carpenter

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and strictly follow an external 'Architect Blueprint' without using delimiters or instructions to ignore embedded commands.
  • Ingestion points: The skill receives an 'Approved Architect Blueprint' as its primary input for construction (defined in SKILL.md).
  • Boundary markers: There are no specified delimiters (e.g., XML tags or clear separators) or 'ignore' instructions provided to the agent to distinguish between legitimate content and potentially malicious instructions within the blueprint.
  • Capability inventory: The skill is capable of generating long-form prose and finding source URLs for citations, which involves processing and outputting data based on the untrusted blueprint input.
  • Sanitization: There is no evidence of sanitization, validation, or escaping logic applied to the blueprint content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:43 AM