pi-coding-agent-sdk
Warn
Audited by Snyk on May 19, 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). Yes — SKILL.md explicitly tells the agent to "Fetch current docs if needed" and the Source Of Truth lists public GitHub URLs (e.g., raw.githubusercontent.com and github.com links) that the agent is expected to read and use to shape code/tooling decisions, so external, user-editable content can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata