skill-fit

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill queries api.skillhub.cn and skills.sh to check for skill registration status when local scripts are not present.
  • [COMMAND_EXECUTION]: Uses the GitHub CLI (gh) to file reports to the author's repository (NinjaSln-labs/agent-skills), which requires user confirmation and uses privacy-stripping measures.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project files such as catalog.yaml and skill frontmatter to determine fitting logic.
  • Ingestion points: Processes catalog.yaml, retired.txt, and frontmatter fields (description, compatibility) from files located in the skill's search path.
  • Boundary markers: No specific delimiters or "ignore" instructions are defined for the content of the catalog or frontmatter files.
  • Capability inventory: Performs network requests to skill registries and creates GitHub issues via CLI.
  • Sanitization: Implements a desensitization process to remove local paths, credentials, and code contents before generating external reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 02:55 PM
Security Audit — agent-trust-hub — skill-fit