architect-research
Warn
Audited by Snyk on Jul 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: 0.85). SKILL.md step 3 (“Fan out”) dispatches researchers with
web_search="live"to fetch and read outsider-authored web pages/snippets at runtime, which the researchers then write into the agent’s LLM context as markdown findings (free text from external sources).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata