readme-generator
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are professional and documentation-focused, explicitly prohibiting the agent from inventing technical details (hallucination) or performing unauthorized git operations like commits or pushes.\n- [COMMAND_EXECUTION]: To ensure documentation accuracy, the skill requires the agent to verify that commands and usage examples work as written and to capture actual CLI output, implying the execution of local commands within the workspace environment.\n- [PROMPT_INJECTION]: The skill scans repository files (manifests, scripts, tests, type definitions) to extract project details, which presents an attack surface for indirect prompt injection if those files contain malicious instructions. However, the risk is inherent to the skill's primary function.\n
- Ingestion points: Repository manifests, scripts, tests, type definitions, and entry points as specified in the instructions.\n
- Boundary markers: No explicit boundary markers or 'ignore' instructions for the processed content are mentioned.\n
- Capability inventory: The skill is configured with 'workspace-write' sandbox permissions and involves local command execution for verification.\n
- Sanitization: No sanitization of the extracted content is specified before it is processed by the agent.
Audit Metadata