inbound-plan-work

Warn

Audited by Snyk on Aug 4, 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). In inbound-plan-work (skill.md steps 1-8), the agent reads the target “issue, plan document, parent chain, project, linked goals, blockers, and comments” from the Paperclip control plane, which can include outsider-authored free text in those comments/documents at runtime.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 4, 2026, 08:26 PM
Issues
1
Security Audit — snyk — inbound-plan-work