skill-supply-chain-audit

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow runs a static scanner that directly reads and parses text files inside an outsider-supplied target skill package directory (e.g., SKILL.md and other .md/.py/.js/etc files) via scripts/audit_skill.py→scan()→entry.read_bytes()/parse_frontmatter() and therefore could ingest arbitrary attacker-authored free text.