skill-builder

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources, including documentation websites, GitHub repositories, PDFs, and local codebases. This creates a surface where malicious instructions embedded in the source material could potentially influence the agent's behavior during the skill creation or enhancement process.
  • Ingestion points: Tools such as scrape_docs, scrape_github, scrape_pdf, scrape_video, and scrape_codebase take external URLs, file paths, and transcripts as input (SKILL.md).
  • Boundary markers: The instructions do not specify any explicit delimiters or 'ignore' instructions for the data being processed.
  • Capability inventory: The skill has access to tools for scraping, AI-powered enhancement (enhance_skill), and deployment (package_skill, upload_skill, install_skill) (SKILL.md).
  • Sanitization: There is no mention of sanitization or validation of the content fetched from external sources before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 04:00 AM
Security Audit — agent-trust-hub — skill-builder