Audit AI coding agents and project configurations for security flaws using static analysis, custom rules, and LLM-assisted verification.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- C · 59 → D · 67
- A · 0 → C · 59
No known CVEs for this server.
- high dangerous code
committed secret: committed .env, Google API key, Anthropic key
analyzed commit 4eea66c · analyzer v33 · 1d ago
danger signals6
- committed secret committed .env muhamedali7713-agent-audit-4eea66c/benchmarks/incident-corpus.zip!/incident-corpus/comment-and-control-github-actions-prompt-injection-2026-04/project/.env :1
env file shipped with populated values - committed secret committed .env muhamedali7713-agent-audit-4eea66c/benchmarks/incident-corpus.zip!/incident-corpus/github-mcp-prompt-injection-private-repo-exfil-2025-05/project/.env :1
env file shipped with populated values - committed secret committed .env muhamedali7713-agent-audit-4eea66c/benchmarks/incident-corpus/comment-and-control-github-actions-prompt-injection-2026-04/project/.env :1
env file shipped with populated values - committed secret committed .env muhamedali7713-agent-audit-4eea66c/benchmarks/incident-corpus/github-mcp-prompt-injection-private-repo-exfil-2025-05/project/.env :1
env file shipped with populated values - committed secret Google API key muhamedali7713-agent-audit-4eea66c/src/agent_audit/knowledge/rule_packs/atr/context-exfiltration/ATR-2026-00021-credential-and-secret-exposure-in-agent-output.yaml :163
AIzaSy…(39 chars, redacted) - committed secret Anthropic key muhamedali7713-agent-audit-4eea66c/tests/smoke_test.py :481
sk-ant…(51 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:muhamedali7713/agent-audit/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of muhamedali7713.