cleanup
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it analyzes content from the codebase and allows an AI agent to perform direct file modifications based on that content.\n
- Ingestion points: Source code files in the project directory are read and analyzed by a sub-agent.\n
- Boundary markers: There are no markers or instructions provided to the sub-agent to distinguish between code and potential malicious instructions embedded within that code.\n
- Capability inventory: The sub-agent is granted the authority to make direct edits to files within the project scope.\n
- Sanitization: There is no mechanism to sanitize or validate the content of the files before the agent processes them, nor is there a mandatory review step for the direct edits.\n- [COMMAND_EXECUTION]: The skill involves the execution of filesystem commands such as
mkdir -pto organize project reports.
Audit Metadata