codedrobe-adapter-dev

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the author-provided codedrobe CLI tool to interact with local applications and the file system. These actions are intended for development and involve vendor-managed resources.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) when processing data from external applications.
  • Ingestion points: Application DOM structures are ingested using the codedrobe dom snapshot command.
  • Boundary markers: Documentation specifies the exclusion of textual content, form values, and accessible names from snapshots.
  • Capability inventory: The execution environment includes the codedrobe CLI, which can perform process management, local network connections, and file system writes.
  • Sanitization: The tool filters out content layers that typically carry prompt injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 10:05 PM
Security Audit — agent-trust-hub — codedrobe-adapter-dev