code-documentation-doc-generate
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by analyzing source code, configuration files, and comments, which are external and untrusted inputs that could contain instructions designed to manipulate the agent's behavior.
- Ingestion points: Instructions in
SKILL.mddirect the agent to 'Extract information from code, configs, and comments.' - Boundary markers: The skill does not specify any delimiters or instructions for the agent to ignore potentially adversarial content within the parsed code.
- Capability inventory: The skill's workflow involves executing shell commands for builds and making network calls for API documentation (
SKILL.md). - Sanitization: There is no mention of technical sanitization or validation for the data extracted from the codebase beyond a general instruction to avoid secrets.
- [COMMAND_EXECUTION]: The instructions and worked examples in
SKILL.mdrequire the agent to 'run the existing schema/doc build' and execute 'documented read-only calls.' While consistent with the skill's purpose, this capability involves executing commands that could be exploited if not constrained.
Audit Metadata