doc-specialist
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests scraped public documentation produced by the web-scraper workflow (see SKILL.md "Integration with web-scraper" —
scrape_docs.py URL -o biblioteca/nombre/) and generate_specialist.py reads INDEX.md, FULL_DOCS.md and individual*.mdfiles to build agent instructions (templates/specialist_base.md) that instruct the agent to consult those docs, so arbitrary third‑party content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata