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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 15, 2026, 10:07 AM
Issues
1