cpu-profiler-config

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill provides a surface for indirect prompt injection as it processes external performance data with powerful tools.\n
  • Ingestion points: The 'Read' tool is utilized to access configuration and profiling data (SKILL.md).\n
  • Boundary markers: Absent; no delimiters or warnings are used to isolate untrusted data.\n
  • Capability inventory: Access to 'Bash', 'Write', 'Edit', and 'Read' tools is granted.\n
  • Sanitization: Absent; no input validation or escaping is specified.\n- [No Code] (SAFE): The skill consists only of a markdown definition file and contains no scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 06:29 PM