ai-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external visual content (images and videos) to determine metadata and tags. This creates an attack surface for indirect prompt injection if the visual content contains adversarial text designed to override the configured instructions.
- Ingestion points: Images and videos processed via the task types in SKILL.md and resources/EXAMPLES.md.
- Boundary markers: The instructions do not include explicit delimiters or safety instructions.
- Capability inventory: Adding/removing tags and setting custom metadata fields in ImageKit DAM.
- Sanitization: No explicit validation of AI-generated tags described.
- [NO_CODE]: No executable scripts or source code files were found within the skill package; it consists primarily of documentation and configuration examples.
Audit Metadata