meeting-personas
Warn
Audited by Snyk on Mar 5, 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). The skill explicitly fetches and ingests user-generated content from referenced GitLab/GitHub issues (Step 1: "Fetch the issue details ... Read the issue description, labels, comments, and linked MRs") and uses that content as core meeting context that can influence sub-agent prompts and decisions, so untrusted third-party text could inject instructions indirectly.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs fetching GitHub/GitLab issue details at runtime (e.g., https://github.com///issues/ or https://gitlab.com///-/issues/), and that fetched issue content is injected into sub-agent prompts to directly control the agents' behavior.
Audit Metadata