agent-project-guidelines-example
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The file
sub-skills/claude-ai-integration-structured-output.mdcontains an LLM integration pattern that is vulnerable to indirect prompt injection. 1. Ingestion point: Thecontentparameter in theanalyze_with_agentfunction. 2. Boundary markers: Absent; untrusted input is passed directly into the user message content. 3. Capability inventory: The function utilizes theanthropicclient to call an LLM and parse the response into structured Pydantic models. 4. Sanitization: Absent; there is no validation or escaping of external content before interpolation. - COMMAND_EXECUTION (LOW): Multiple files, including
sub-skills/deployment-commands.md,sub-skills/backend-pytest.md, andsub-skills/frontend-react-testing-library.md, contain shell commands for deployment (gcloud run deploy), environment management (poetry run), and testing. These are standard for the skill's purpose as a project guideline but represent a high-privilege execution surface. - SAFE (SAFE): The
sub-skills/environment-variables.mdfile contains credential patterns likesk-ant-...andeyJ.... These are identified as non-functional placeholders used for documentation purposes and do not represent actual hardcoded secrets.
Audit Metadata