Orphan Files Cleanup
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for a maintenance task and does not include executable code, remote downloads, or hidden payloads.- [COMMAND_EXECUTION]: The instructions direct the agent to run standard repository commands such as build, test, and lint to validate project integrity after file removal. These are benign development practices.- [PROMPT_INJECTION]: While the skill ingests project data (source code and configuration files), it includes explicit defensive constraints such as 'Do not delete what you cannot verify' and requires the agent to confirm project stability using existing scripts, addressing potential indirect prompt injection risks.
Audit Metadata