agent-motion-designer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data via the
$ARGUMENTSplaceholder at the end of its instructions without boundary markers. - Ingestion points:
SKILL.mdvia the$ARGUMENTSvariable. - Boundary markers: Absent. No delimiters are used to separate user input from system instructions.
- Capability inventory: None. The skill does not define any scripts, shell commands, or tool usage.
- Sanitization: Absent. User input is interpolated directly.
- [NO_CODE]: The skill is composed entirely of markdown instructions and metadata, containing no scripts or executable logic.
Audit Metadata