fixing-motion-performance
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a command to review user-supplied files, which introduces an indirect prompt injection surface where code comments or data within those files could attempt to influence the agent's behavior.
- Ingestion points: User-provided files processed via the
/fixing-motion-performance <file>command defined in SKILL.md. - Boundary markers: The skill does not specify any delimiters or instructions for the agent to ignore potential instructions embedded within the files being reviewed.
- Capability inventory: The instructions are limited to reviewing and providing feedback; no dangerous file-writing or network tools are invoked in the skill body.
- Sanitization: There is no requirement or instruction to sanitize the file content before it is processed by the agent.
Audit Metadata