creative-brief-and-big-idea
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data including business problems, audience research, and social listening themes. This creates a potential surface for indirect prompt injection if malicious instructions are embedded in the ingested data.
- Ingestion points: Input sources are defined in
SKILL.md, including 'Business problem', 'Audience evidence', and 'Social listening themes'. - Boundary markers: The skill does not explicitly define delimiters for untrusted data, though it references an
anti-ai-slopquality gate for output validation. - Capability inventory: The skill is restricted to analysis and drafting work; no dangerous capabilities such as file writing, network exfiltration, or subprocess execution are present in the skill files.
- Sanitization: No specific input sanitization or filtering logic is described in the workflow.
Audit Metadata