perf-review
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Required workflow runs
scripts/analyze.py, which reads outsider-authored free text from the user’s own Claude history files (~/.claude/history.jsonland~/.claude/projects/*/*.jsonl) and then injects extracted prompt/message text samples into the LLM context via the generated/tmp/perf-review.jsonthat the skill uses to produce the inline report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata