NYC

grepai-trace-callees

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): The skill consists entirely of markdown documentation and usage examples for a code analysis tool. No malicious code, obfuscation, or credential exfiltration attempts were found.
  • [COMMAND_EXECUTION] (SAFE): The skill describes using the 'grepai' command-line utility and standard utilities like 'jq' and 'grep' for processing tool output. This behavior is consistent with the intended primary purpose of the skill for code analysis and discovery.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill involves reading and processing source code which could contain malicious instructions. 1. Ingestion points: Source code files processed by grepai. 2. Boundary markers: None specified in the documentation. 3. Capability inventory: Local shell command execution for code analysis. 4. Sanitization: None specified. This is a known risk surface for code analysis tools but is categorized as safe here as it is the core functionality of the tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:54 PM