write-skill
Warn
Audited by Snyk on Apr 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill explicitly uses prompt preprocessing via
!`command(e.g., "Diff: !gh pr diff", "Analysis: !python ${CLAUDE_SKILL_DIR}/scripts/analyze.py" in frontmatter/preprocessing examples) which injects external, user-generated content (PR diffs/CLI/API outputs) into the agent prompt and therefore could allow indirect prompt injection from untrusted third-party sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata