gitsafehub
github.com/0xr10t/mcp-agent ↗

0xr10t/mcp-agent

scanned 2026-07-30 · git 99b8840
2 of 6 checks flagged a security issue
🔴 Needs attention
Only 3 of 6 checks finished — treat this as provisional. Re-check ↻

Informational scan, not a security audit. How this is computed.

Leaked secrets15Vulnerable dependencies124Known OSS vulnerabilities—Risky code patterns✓Malicious dependencies—Project health—

Security checks

Leaked secrets — Gitleaksⓘ 15 found · 1 serious

API keys, passwords or tokens committed into the repo.

  • Serious github-fine-grained-pat Found a GitHub Fine-Grained Personal Access Token, risking unauthorized repository access and code manipulation.
    examples/mcp/mcp_websockets/mcp_agent.config.yaml:22
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    src/mcp_agent/cli/README.md:82
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    examples/mcp_agent_server/asyncio/README.md:206
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    src/mcp_agent/cli/README.md:84
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/fixtures/api_test_utils.py:135
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/secrets/test_api_client_type.py:16
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/secrets/test_api_client.py:23
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/secrets/test_api_client.py:178
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/secrets/test_api_client.py:183
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/test_api_key_rename.py:34
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/utils/jwt_generator.py:120
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/commands/test_configure.py:108
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/commands/test_configure.py:109
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/commands/test_configure.py:286
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.
  • Worth fixing generic-api-key Detected a Generic API Key, potentially exposing access to various services and sensitive operations.
    tests/cli/commands/test_configure.py:287
    A credential (key, password or token) appears in your code. Fix: Remove it, rotate the key, and load it from an environment variable instead.

via Gitleaks v8.21.2 · MIT

Vulnerable dependencies — Trivyⓘ 124 found · 3 serious

Packages you depend on that have known security holes (CVEs).

  • Serious CVE-2025-68664 langchain-core: LangChain: Arbitrary code execution via serialization injection
    uv.lock
    A package you depend on has a known security hole (CVE-2025-68664). Fix: Update that package to its patched version.
  • Serious CVE-2026-35030 litellm: LiteLLM: Authentication bypass and privilege escalation via OIDC userinfo cache key collision
    uv.lock
    A package you depend on has a known security hole (CVE-2026-35030). Fix: Update that package to its patched version.
  • Serious CVE-2026-49468 litellm: LiteLLM: Authentication Bypass via Host Header Injection
    uv.lock
    A package you depend on has a known security hole (CVE-2026-49468). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-69223 aiohttp: AIOHTTP's HTTP Parser auto_decompress feature is vulnerable to zip bomb
    uv.lock
    A package you depend on has a known security hole (CVE-2025-69223). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-69227 aiohttp: aiohttp: Denial of Service via specially crafted POST request
    uv.lock
    A package you depend on has a known security hole (CVE-2025-69227). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-69228 aiohttp: aiohttp: Denial of Service via memory exhaustion from crafted POST request
    uv.lock
    A package you depend on has a known security hole (CVE-2025-69228). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-69229 aiohttp: AIOHTTP: Denial of Service via excessive CPU usage in chunked message handling
    uv.lock
    A package you depend on has a known security hole (CVE-2025-69229). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-22815 aiohttp: AIOHTTP: Denial of Service via insufficient header/trailer handling
    uv.lock
    A package you depend on has a known security hole (CVE-2026-22815). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-34515 aiohttp: AIOHTTP: Information disclosure via static resource handler on Windows
    uv.lock
    A package you depend on has a known security hole (CVE-2026-34515). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-34516 aiohttp: AIOHTTP: Denial of Service via excessive multipart headers
    uv.lock
    A package you depend on has a known security hole (CVE-2026-34516). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-34525 aiohttp: aiohttp: Security bypass via multiple Host headers
    uv.lock
    A package you depend on has a known security hole (CVE-2026-34525). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-34993 aiohttp: AIOHTTP: Arbitrary code execution via untrusted input to CookieJar.load()
    uv.lock
    A package you depend on has a known security hole (CVE-2026-34993). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-47265 python-aiohttp: AIOHTTP: Information disclosure via improper handling of cookies during cross-origin redirects
    uv.lock
    A package you depend on has a known security hole (CVE-2026-47265). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-54273 aiohttp: AIOHTTP: Denial of Service via excessive pipelined requests
    uv.lock
    A package you depend on has a known security hole (CVE-2026-54273). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-54274 aiohttp: aiohttp: Denial of Service via incomplete websocket frame payloads
    uv.lock
    A package you depend on has a known security hole (CVE-2026-54274). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-54276 aiohttp: aiohttp: Information disclosure via DigestAuthMiddleware after cross-origin redirect
    uv.lock
    A package you depend on has a known security hole (CVE-2026-54276). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-54277 aiohttp: aiohttp: Denial of Service via oversized HTTP request lines bypassing max_line_size check
    uv.lock
    A package you depend on has a known security hole (CVE-2026-54277). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-54278 aiohttp: aiohttp: Denial of Service due to excessive memory consumption from compressed request body
    uv.lock
    A package you depend on has a known security hole (CVE-2026-54278). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-21226 Azure Core is vulnerable to deserialization of untrusted data
    uv.lock
    A package you depend on has a known security hole (CVE-2026-21226). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-26007 cryptography: cryptography Subgroup Attack Due to Missing Subgroup Validation for SECT Curves
    uv.lock
    A package you depend on has a known security hole (CVE-2026-26007). Fix: Update that package to its patched version.
  • Worth fixing GHSA-537c-gmf6-5ccf Vulnerable OpenSSL included in cryptography wheels
    uv.lock
    A package you depend on has a known security hole (GHSA-537c-gmf6-5ccf). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-39892 cryptography: Cryptography: Buffer overflow via non-contiguous buffer in API
    uv.lock
    A package you depend on has a known security hole (CVE-2026-39892). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-68146 filelock: filelock: Time-of-Check-Time-of-Use (TOCTOU) race condition and symlink attack allows arbitrary file corruption or truncation
    uv.lock
    A package you depend on has a known security hole (CVE-2025-68146). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-22701 filelock: filelock Time-of-Check-Time-of-Use (TOCTOU) in SoftFileLock
    uv.lock
    A package you depend on has a known security hole (CVE-2026-22701). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-2472 google-cloud-aiplatform: google-cloud-aiplatform: Arbitrary code execution via Stored Cross-Site Scripting (XSS)
    uv.lock
    A package you depend on has a known security hole (CVE-2026-2472). Fix: Update that package to its patched version.
… 99 more not shown

via Trivy v0.70.0 · Apache-2.0

Known OSS vulnerabilities — OSV-Scannerⓘ timed out

Your dependencies cross-checked against the OSV vulnerability database.

This check didn’t finish — that’s not the same as “clean.” Try Check again above.

via OSV-Scanner v1.9.2 · Apache-2.0

error: timeout after 400s

Risky code patterns — Semgrepⓘ none found ✓

Code that can be exploited: injection, hardcoded credentials and similar.

Nothing found by this check. ✓

via Semgrep v1.147.0 · LGPL-2.1

Malicious dependencies — Guarddogⓘ timed out

Packages that look intentionally malicious: typosquats, sneaky install scripts.

This check didn’t finish — that’s not the same as “clean.” Try Check again above.

via Guarddog v2.10.0 · Apache-2.0

error: pypi:timeout

Project health

A signal about how the project is maintained — not a vulnerability in your code. It doesn’t affect the verdict above.

Project health — OpenSSF Scorecardⓘ didn’t run

Maintenance & supply-chain hygiene. A signal about the project, not a vulnerability in your code.

This check didn’t finish — that’s not the same as “clean.” Try Check again above.

via OpenSSF Scorecard · Apache-2.0

About these results. Six open-source checks ran in parallel; every finding is tagged with the tool that produced it. The verdict follows a published rule. False positives and false negatives are normal — a clean scan does not mean the code is secure, and a red verdict does not mean the project is compromised.