web-security-headers
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the $ARGUMENTS placeholder to incorporate external input into its context instructions, creating a surface for indirect prompt injection.
- Ingestion points: Interpolation of $ARGUMENTS in the 'Context' section of SKILL.md.
- Boundary markers: None present; the input is not delimited with specific tags to distinguish it from instructions.
- Capability inventory: None; the skill consists entirely of instructional text and does not provide scripts, automated tool invocations, or file-writing capabilities.
- Sanitization: None; the instructions do not specify any validation or filtering for the external input.
Audit Metadata