performance-profiler
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: 0.70). The skill explicitly ingests and interprets user-provided profiler output as part of Mode 2 ("Profile Step 1: Parse" in SKILL.md) using scripts/profile-parser.py, so arbitrary untrusted/user-generated text can directly influence hotspot identification and subsequent recommendations.
Audit Metadata