agent-research
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a runtime workflow that starts a Nimble web-research “run” (
nimble_agent_run_start) and later retrieves the terminal answer with cited web sources (nimble_agent_run_result), so outsider-authored free text can be ingested during the research.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata