skillkit-help

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is an educational resource intended to guide users through the process of creating and validating Claude Skills. It contains no executable logic or sensitive data access.
  • [NO_CODE]: No scripts or executables are included in the skill package; all instructions are provided in markdown format.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a validation workflow that reads user-provided skill files, creating a potential surface for indirect prompt injection. However, this is considered a low risk due to the skill's narrow scope and lack of high-privilege automated capabilities. (1) Ingestion points: User-provided content or file paths in SKILL.md (Path B). (2) Boundary markers: None present. (3) Capability inventory: Filesystem read access (view). (4) Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 04:37 PM