packify
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of prompt-based instructions and metadata. It does not include any scripts, binaries, or automated network operations that could pose a security risk.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied images and instructs the agent to preserve visible typography and branding. This creates an inherent surface for indirect prompt injection if an image contains malicious text commands, though the impact is mitigated by the skill's narrow focus on image generation.
- Ingestion points: User-supplied images defined as the "sole authority" for identity in SKILL.md.
- Boundary markers: No explicit delimiters are defined for content extracted from images.
- Capability inventory: Limited to image analysis and image generation via platform tools.
- Sanitization: None provided; the skill relies on the underlying AI model's safety guardrails.
Audit Metadata