code-documentation-doc-generate
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill's instructions require the agent to 'Extract information from code, configs, and comments'. Configuration files (such as
.env,.yaml, or.jsonfiles) frequently contain sensitive information including API keys, database credentials, and internal service URLs. This behavior facilitates the exposure of local sensitive data to the agent's context during the documentation process. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the codebase without technical isolation.
- Ingestion points: The agent is instructed to read all files in the repository, including source code, comments, and configuration files (referenced in
SKILL.mdandresources/implementation-playbook.md). - Boundary markers: There are no explicit markers or XML tags defined to separate the untrusted code content from the agent's instructions, increasing the risk that the agent will follow malicious instructions embedded in comments.
- Capability inventory: The skill performs file reading and metadata extraction across the entire project structure.
- Sanitization: No technical sanitization or validation of the code content is present; the skill relies solely on a high-level safety instruction to 'Avoid exposing secrets'.
Audit Metadata