strategic-reading
Warn
Audited by Snyk on May 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). High likelihood: the skill ingests “Source text” at runtime from outsider-authored documents (e.g., EPUB/PDF/article via
web_fetchor downloaded files), then extracts readable prose (BeautifulSoup /pdftotext -layout/ web page text) into the agent’s LLM context for triage and deep read.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata