05-creative
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted external data to drive its content generation flow.
- Ingestion points: The skill reads strategy documents from Notion (voice, signature, facts) and cards from an Idea Pool (hook, format, pillar, proof, notes) as specified in
SKILL.md. - Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded within the external Notion or Idea Pool data.
- Capability inventory: The skill has the ability to read internal reference files, invoke other design-related skills, and interact with external platforms like Figma and Notion.
- Sanitization: Absent. There is no mention of sanitizing, escaping, or validating the data retrieved from external sources before it is used to influence the agent's creative output.
Audit Metadata