thinkies-cite-sources

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user input ($ARGUMENTS) and information retrieved from the web to produce citations, which presents an indirect prompt injection surface.
  • Ingestion points: SKILL.md targets user arguments and external information retrieved via web search or APIs.
  • Boundary markers: None provided to isolate untrusted content.
  • Capability inventory: Uses WebFetch, web search, and API lookup tools.
  • Sanitization: No content sanitization is specified for retrieved source material.
  • [COMMAND_EXECUTION]: The README.md file provides an installation command using 'npx' to add the skill from the vendor's GitHub repository.
  • [EXTERNAL_DOWNLOADS]: The skill references and links to an external '.skill' package hosted on the author's GitHub repository for manual installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:28 AM
Security Audit — agent-trust-hub — thinkies-cite-sources