skills/softspark/ai-toolkit/biz-scan/Gen Agent Trust Hub

biz-scan

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted codebase data.\n
  • Ingestion points: Source code files are read and searched using the Read and Grep tools.\n
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to ignore instructions embedded within the codebase content.\n
  • Capability inventory: The skill's permissions are restricted to Read, Grep, and Glob; it has no ability to write files, execute arbitrary code, or perform network operations.\n
  • Sanitization: Content from the codebase is processed without prior validation or escaping.\n- [COMMAND_EXECUTION]: The skill executes shell-based search commands (grep) to locate data models, API endpoints, and tracking events. These commands are static and scoped to the project directory, representing standard diagnostic behavior for a business intelligence agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:07 AM
Security Audit — agent-trust-hub — biz-scan