product-choreography
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of markdown instructions and reference files for creative storytelling and animation design. It does not utilize any tools, scripts, or external network resources.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided product descriptions and competitive claims to generate beat sheets. While this represents a data ingestion surface, the skill lacks any capabilities (such as tool usage, file system writes, or network access) that could be exploited via malicious input. The risk is limited to the agent generating off-topic text within its own responses.
- Ingestion points: User-supplied product details, competitive claims, and potential 'CONVERSION SPEC' documents (SKILL.md).
- Boundary markers: None explicitly defined for untrusted text.
- Capability inventory: No tools, shell commands, or network operations are enabled or used.
- Sanitization: Not present, but impact is negligible due to lack of sensitive capabilities.
Audit Metadata