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, andscrape_codebasetake 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