cms-tokens-authentication
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided use cases and requirements to generate authentication advice. While there are no specific boundary markers for this untrusted input, the skill's capabilities are restricted to read-only advisory tasks using basic search tools (Read, Grep, Glob), and it contains explicit instructions to never suggest bypassing security controls.
- Ingestion points: User requests defining use cases (frontend, backend, CI/CD, etc.) in
SKILL.md. - Boundary markers: Absent.
- Capability inventory: Limited to
Read,Grep, andGlobtools for information retrieval. No file-writing, network-sending, or code-execution capabilities. - Sanitization: The instructions explicitly mandate the use of placeholders for secrets and adherence to security policies.
Audit Metadata