storm-research
Warn
Audited by Snyk on Jun 30, 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 Phase 1 and Phase 4 explicitly instruct the runtime to do “real web research” and to “verify a citation against its PRIMARY source” by fetching primary URLs; those fetched pages are outsider-authored free text that the agent LLM ingests into its context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata