fixing-motion-performance
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied files via the /fixing-motion-performance command, which introduces a surface for indirect prompt injection where malicious instructions embedded in a reviewed file could attempt to influence the agent. * Ingestion points: File paths provided as arguments to the review command. * Boundary markers: None specified in the instructions to separate untrusted file content from system guidelines. * Capability inventory: The skill is limited to providing analysis reports and code-level suggestions; it lacks capabilities for network access, file system modification, or arbitrary command execution. * Sanitization: No evidence of input validation or sanitization for the content of processed files.
Audit Metadata