perform-like-jeff-and-sanjay
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-based guide that provides a methodology for performance optimization. No malicious instructions, obfuscation, or risky operations were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze project-related files (code, tests, and configuration), which is a common surface for indirect prompt injection.\n
- Ingestion points: SKILL.md Step 1 (project rules, target code, callers, tests, and deployment shapes).\n
- Boundary markers: Not explicitly defined in the instructions.\n
- Capability inventory: The skill is analytical in nature and does not request specific dangerous capabilities like network access or arbitrary command execution.\n
- Sanitization: The skill relies on the agent's default safety mechanisms.
Audit Metadata