lpm-guide

Warn

Audited by Snyk on Mar 10, 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). This skill explicitly instructs the agent to scan public GitHub/GitLab issues and extract recurring bug workarounds and FAQs (see sections/skills.md, Step 1b "Scan GitHub/GitLab Issues (Best-Effort)"), which means it will fetch and ingest untrusted, user-generated content that can directly shape generated Agent Skills and subsequent agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 11:21 PM