verification
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it ingests and acts upon untrusted data (source code changes) from the local environment.
- Ingestion points: Reads uncommitted and committed code changes from the local repository as specified in the execution instructions.
- Boundary markers: Absent. The skill does not define clear delimiters or instructions to ignore natural language commands embedded within the code or comments it reviews.
- Capability inventory: The skill has access to
Bash,Write,Edit, andReadtools, providing a wide range of actions that could be misdirected by injected instructions. - Sanitization: None. There is no evidence of filtering or escaping logic applied to the source code before it is passed to the review or fix skills.
- [COMMAND_EXECUTION]: Employs the
Bashtool to programmatically check for active development servers on specific local ports (3000, 5173, 8080) to facilitate automated testing.
Audit Metadata