fix-bug
Warn
Audited by Snyk on Mar 9, 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). This skill explicitly fetches and ingests GitHub issue content (SKILL.md Step 1: “gh issue view ... --json title,body,labels,comments,state”) and then requires the agent to analyze those user-generated issue bodies/comments to decide what code to change and what actions to take (Steps 2–6), so untrusted third-party content can materially influence behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches GitHub issue content at runtime (e.g., https://github.com/owner/repo/issues/123 via
gh issue view) and then uses that issue body/steps to drive the agent's analysis and actions, so external content can directly control prompts and behavior.
Audit Metadata