production-designer

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'renku' CLI to perform all production design tasks. This includes project resolution ('renku project current'), context reading ('renku production-design location context'), and data mutation ('renku location apply'). These operations are restricted to the vendor-owned 'renku' toolset.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external JSON files and CLI command outputs, representing a potential data ingestion surface.
  • Ingestion points: The agent reads JSON data from local files via '--file' arguments (e.g., location-operations-json) and captures shell command outputs formatted as JSON.
  • Boundary markers: The instructions do not explicitly define delimiters to separate ingested data from agent instructions.
  • Capability inventory: The agent has the capability to read and write design facts and design documents using the 'renku' CLI.
  • Sanitization: The skill incorporates mandatory validation steps ('renku location validate') and dry-run flags ('--dry-run') before persistent changes are applied, acting as a control against malformed or malicious data structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 08:46 AM
Security Audit — agent-trust-hub — production-designer