api-writer
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or associated templates. The skill's primary function is text-based documentation generation.
- [DATA_EXPOSURE]: The skill gathers context by scanning local files like PRDs and existing API specifications using glob patterns. This is restricted to the execution environment and includes a mandatory step to ask for user confirmation before reading documents, aligning with the principle of informed consent.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (product requirements) which presents a theoretical surface for indirect prompt injection. However, the risk is mitigated because the skill's capabilities are limited to generating documentation and it does not possess tools for code execution or network exfiltration.
- [COMMAND_EXECUTION]: No unauthorized or dangerous command execution patterns were found. The mention of 'TodoWrite' appears to be a status tracking mechanism for the agent's internal progress rather than a shell execution tool.
Audit Metadata