troubleshooting

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The skill's required troubleshooting workflow (SKILL.md, "Search for Similar Issues" step) explicitly instructs the agent to consult public web sources — "Google exact error message", "Check GitHub issues", and "Search Stack Overflow" — which are untrusted, user-generated sources the agent would read and could use to drive further actions, enabling indirect prompt injection risk.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 06:47 PM