docs-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any malicious code, unauthorized command execution, or network exfiltration. The instructions and examples are focused purely on generating docstrings, README files, and changelogs. All external links point to the author's verified GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes source code, which serves as an ingestion point for untrusted data. While inherent to documentation tools, users should be aware that adversarial comments within analyzed code could potentially influence agent behavior.
- Ingestion points: Local source code files, including docstrings and existing documentation as described in SKILL.md.
- Boundary markers: The skill does not define explicit delimiters to separate untrusted code data from the agent's internal instructions.
- Capability inventory: The skill uses platform tools to read files and generate documentation output on the local file system.
- Sanitization: No specific logic is included to sanitize or filter potential instructions embedded within the source code being documented.
Audit Metadata