agent-perf-analyzer

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate static analysis for Ascend NPU environments. All analyzed code remains local and no data exfiltration was detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local code files, creating a surface for indirect prompt injection. 1. Ingestion points: Local files are read in scripts/analyze_precision.py and scripts/analyze_performance.py. 2. Boundary markers: None present; code snippets are directly included in reports. 3. Capability inventory: The skill uses subprocess calls to execute its own analyzer scripts on target code. 4. Sanitization: No sanitization or escaping is performed on extracted code snippets before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:24 AM
Security Audit — agent-trust-hub — agent-perf-analyzer