design-and-templates
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external identity and content data which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads external data from
brand-profileand user-definedrecurring content needsas specified inSKILL.md. - Boundary markers: There are no instructions for the agent to use specific delimiters or to treat the ingested data as potentially untrusted content to prevent the agent from following instructions embedded within the data.
- Capability inventory: The skill generates briefs and prompts that influence the actions of downstream agents and tools, including
image-promptfor image generation and theWoopSocialflow for publishing content. - Sanitization: The instructions lack specific guidance for the agent to sanitize, escape, or validate the content extracted from the brand profile or content needs before using it to generate downstream instructions.
Audit Metadata