doc-generator
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted Python source files, creating a surface for indirect prompt injection via docstrings or comments.\n
- Ingestion points: Python source files and directories provided by the user (SKILL.md).\n
- Boundary markers: Absent; no delimiters are used to separate docstring content from agent instructions.\n
- Capability inventory: The skill uses
ast,inspect, andpathlibfor code analysis and file system access (SKILL.md).\n - Sanitization: Absent; the skill does not specify any filtering or validation of the extracted docstrings.\n- [COMMAND_EXECUTION]: The instructions recommend using the
inspectmodule for runtime introspection. This technique involves importing the Python modules being analyzed, which executes any code residing at the module's top level.
Audit Metadata