todos-to-issues
Warn
Audited by Snyk on Feb 21, 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 reads upstream repository files (e.g., via "git fetch upstream" and by reading upstream CONTRIBUTING.md, README.md, and .github/ISSUE_TEMPLATE/*) and then uses those untrusted, user-generated templates/guidelines to decide how to format and create GitHub issues, so external content can influence agent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly performs runtime git operations (e.g., "git fetch upstream main:upstream-main") and checks for a GitHub remote (github.com) and then reads upstream CONTRIBUTING.md and .github templates from https://github.com, so fetched remote content is used at runtime to control how the agent formats and creates issue prompts/instructions.
Audit Metadata