usage-rules
Warn
Audited by Snyk on Mar 3, 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's "Progressive fetch" workflow (SKILL.md / README) explicitly fetches packages from hex.pm using commands like "mix hex.package fetch --unpack" and extracts third-party usage-rules.md files, which the agent reads and uses to guide decisions, so untrusted, user-authored content can 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 packages at runtime (via "mix hex.package fetch" and curl for the hex.pm API) and extracts usage-rules.md from hex.pm which are then injected into the agent's context to control prompts — flagged domain: https://hex.pm.
Audit Metadata