acceptance-criteria-builder

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is strictly planning-only and explicitly prohibits the execution of code, scripts, or Blender operations, maintaining an L0 capability tier.
  • [SAFE]: No patterns associated with prompt injection, data exfiltration, obfuscation, or credential exposure were detected in the instructions or reference files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data (briefs and recipes) into the agent's context. However, the risk is minimal as the skill lacks executable capabilities to act on potential malicious instructions within that data.
  • Ingestion points: Locked brief summary and Chosen recipe (SKILL.md).
  • Boundary markers: No delimiters or ignore instructions are defined for the input data.
  • Capability inventory: None; the skill is restricted to text generation for planning purposes.
  • Sanitization: No explicit sanitization or validation of input data is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 01:08 AM