feedback-application
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection. It processes external, potentially untrusted data from code reviews to drive file modifications.
- Ingestion points: Processes 'reviewer notes', 'PR review notes', and 'feedback items' as described in the Workflow section.
- Boundary markers: No explicit delimiters or instructions to treat external input as untrusted data are present.
- Capability inventory: The agent uses 'Edit' and 'Write' tools to modify the codebase and executes 'uv run ruff check' via the shell.
- Sanitization: No sanitization or verification logic is provided to filter malicious instructions embedded within review comments.
- [COMMAND_EXECUTION] (SAFE): The use of 'uv run ruff check' for code validation is a low-risk, standard operation for this type of skill.
Audit Metadata