motion-brief-writer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data, such as brand guides, logo files, and motion references, to generate prompts for Claude Code. This creates an attack surface where instructions hidden within these assets could be processed by the agent.
- Ingestion points: Reads user-supplied ideas, brand assets, and reference materials in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or warnings to ignore commands that might be embedded in the provided brand materials.
- Capability inventory: While the skill itself is a prompt generator, the output is intended for Claude Code, which possesses file system access and shell execution capabilities.
- Sanitization: There is no explicit logic to sanitize or filter potential prompt injection attempts from the text extracted from brand guides or references.
Audit Metadata