research-scout
Warn
Audited by Snyk on Jun 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s REQUIRED workflow ingests only user-provided links (and then fetches/transcribes them at runtime), which are outsider-authored free text (e.g., public web pages or video transcripts) that the agent reads into LLM context via the “Understand the resources” phase (read full article content / fetch full transcript via
transcribe <url>/ examine repo README and files).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata