motion-authoring
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and interpret external "reference site scripts" and the
motion.manifest.jsonfile to replicate animation behavior. This ingestion process is vulnerable to indirect prompt injection, where malicious instructions hidden in comments or strings within the reference code could influence the agent's actions.\n - Ingestion points: External reference site scripts and
motion.manifest.json(as described in Section 0 and Section 2).\n - Boundary markers: Absent. The skill lacks instructions for the agent to isolate or ignore potential natural language commands embedded in the code it is analyzing.\n
- Capability inventory: The agent has the capability to generate code for Next.js, Vite, and Astro, and is instructed to run local build commands such as
vite build,astro build, andnext build.\n - Sanitization: Absent. No validation or filtering steps are defined for the ingested reference material.
Audit Metadata