mindful-precision
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to "exploit available tools (..., web, ...)" in SKILL.md and its Resourcefulness examples (references/RESOURCEFULNESS_EXAMPLES.md) show web searches and fetching arXiv results, meaning the agent is expected to ingest open/public third‑party web content that could influence decisions and enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata