agent-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and reference documents. It does not perform any automated network requests, file system modifications (beyond documentation examples), or execution of external code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review user-provided agent designs and workflows. This ingestion of untrustworthy third-party content creates an indirect prompt injection surface where a malicious design could attempt to influence the reviewing agent's behavior.
- Ingestion points: User-submitted Agent/Skill/Workflow descriptions and designs (SKILL.md Mode 2).
- Boundary markers: The instructions do not define specific delimiters or warnings to separate user-provided content from the agent's core instructions.
- Capability inventory: The skill is restricted to textual analysis and report generation; it does not request tools for network access, arbitrary shell execution, or persistent file storage.
- Sanitization: No input sanitization or filtering logic is specified.
Audit Metadata