skill-finder

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch the current marketplace assistant index from the vendor's official API at https://zynkr.ai/api/skills as a fallback mechanism.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input and external index data to generate command-line recommendations, which creates a potential surface for indirect prompt injection.
  • Ingestion points: User inquiry inputs and the assistant index (local file or API response).
  • Boundary markers: No explicit delimiters are used to separate user data from the recommendation logic.
  • Capability inventory: The skill generates npx skills add commands containing variables derived from the index.
  • Sanitization: There is no evidence of sanitization for strings retrieved from the index before they are placed into shell command templates.
  • [COMMAND_EXECUTION]: The skill generates and displays shell commands (npx skills add) to be executed by the user. These commands reference the author's official repository at https://github.com/peter-tu-zynkr/zynkr-skill-builder.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:30 PM
Security Audit — agent-trust-hub — skill-finder