skills/cniska/skills/skill-test/Gen Agent Trust Hub

skill-test

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown documentation describing a testing workflow. It does not contain any executable scripts, shell commands, or configuration files.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves processing data from external repositories as part of a testing workflow, which serves as a potential ingestion point for untrusted content. 1. Ingestion points: External repositories selected for testing as described in SKILL.md. 2. Boundary markers: The instructions do not specify any delimiters or safety warnings to separate repository content from agent instructions. 3. Capability inventory: No executable tools or dangerous capabilities (such as file-write or network operations) are requested or defined within this skill. 4. Sanitization: No sanitization or filtering of external repository content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 09:15 AM
Security Audit — agent-trust-hub — skill-test