arc-bug-finder
Warn
Audited by Snyk on Jul 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md Step 4 (“Exhaustive Online Research”) instructs using WebSearch/WebFetch to read arbitrary upstream web pages at runtime, which can include outsider-authored free text that the agent would ingest into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata