skill-manager
Warn
Audited by Snyk on May 20, 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 fetches and ingests public, user-generated GitHub content as part of its core workflow—scripts/install.sh clones or sparse-checkouts GitHub repos and scripts/record.py (via get_raw_github_content and fetch_webpage) reads SKILL.md, CHANGELOG.md and commit pages to determine versions/updates—so untrusted third‑party page content is parsed and used to drive install/update decisions, enabling potential indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata