perf
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
- Ingestion points: The skill is designed to analyze and optimize files located in
frontend/andbackend/src/middleware/(SKILL.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that may be embedded within the files it processes.
- Capability inventory: The skill is authorized to use
Read,Edit,Write,Glob,Grep,Bash, andTasktools, which allow for extensive file system modification and command execution (SKILL.md). - Sanitization: No sanitization, validation, or escaping protocols are defined for handling the content of ingested source files before they are processed by the agent.
Audit Metadata