makepad-animation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The
SKILL.mdfile and its metadata use high-priority keywords like 'CRITICAL' and 'Claude MUST' to enforce specific documentation-reading logic. This pattern is often used to override the AI's default instructions or safety boundaries. - Indirect Prompt Injection (LOW): The skill is designed to ingest and process data from local reference files to generate answers, creating a surface for potential instruction injection if those files are modified.
- Ingestion points:
references/animation-system.md,_base/06-animator-basics.md,_base/07-easing-functions.md,_base/08-keyframe-animation.md. - Boundary markers: Absent; the agent is instructed to incorporate content directly into its responses.
- Capability inventory: Limited to code and text generation based on the provided patterns.
- Sanitization: No explicit validation or escaping is applied to the content of the reference files.
Audit Metadata