pi-planning-with-files
Warn
Audited by Snyk on May 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: 0.90). The skill's SKILL.md and templates explicitly require performing "view/browser/search" operations and recording "Research Findings" from web searches/browser results (see the 2-Action Rule and Findings template and examples), meaning the agent ingests open web/browser search output as part of its workflow and then reads that content to guide decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata