claude-code-commands
Warn
Audited by Snyk on Feb 15, 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). The skill's "Issue-Linked Command" (references/patterns.md) explicitly instructs the agent to fetch issue details from third-party issue trackers (e.g., "gh issue view $ARGUMENTS", "jira issue view $ARGUMENTS"), which are user-generated/untrusted sources the agent is expected to read and interpret.
Audit Metadata