codeprobe-architecture

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted source code from user projects while possessing command execution capabilities.
  • Ingestion points: Reads external project files using the Read, Grep, and Glob tools.
  • Boundary markers: Absent; the skill does not define markers or instructions to isolate processed code from agent instructions.
  • Capability inventory: The skill has access to the Bash tool to execute scripts.
  • Sanitization: No sanitization or validation of the ingested content is specified before the agent processes the findings.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script (file_stats.py) to calculate metrics like lines of code and method counts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 12:28 PM