recipe-refactor-to-profile-standards

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs and executes shell commands using python3 .plan/execute-script.py. It interpolates variables such as {expanded_instruction}, {selected_profile}, and {module_name}, which are sourced from project metadata and architecture. If these values contain shell metacharacters (e.g., semicolons, backticks), it could lead to arbitrary command execution.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and acting upon instructions found in project configuration files and metadata.
  • Ingestion points: Project architecture details (modules/packages), status.json metadata, and file discovery results.
  • Boundary markers: The skill does not use delimiters or safety instructions to prevent the agent from obeying instructions embedded within the ingested data.
  • Capability inventory: The skill performs shell command execution through a local wrapper and possesses file-writing capabilities.
  • Sanitization: There is no evidence of validation or escaping for the external data before it is interpolated into the workflow or shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:13 AM
Security Audit — agent-trust-hub — recipe-refactor-to-profile-standards