paper-cuts
Warn
Audited by Snyk on Nov 16, 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). The required Library look-up at line 22 has the agent search upstream issue trackers (GitHub issues are outsider-authored and readable), and the workflow runs without the agent first choosing a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.35). The skill is mainly a reporting workflow, but it tells the agent to "work around" denied tool calls and permissions and to "make the change" to the machine when the user approves a fix, without limiting those changes to non-sudo, project-scoped actions.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata