slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-uploaded images, which creates an ingestion point for untrusted external data. * 1. Ingestion points: The skill instructions in SKILL.md describe using PIL.Image.open to load user-uploaded images. * 2. Boundary markers: No specific delimiters or instructions for the agent to ignore embedded data instructions are provided. * 3. Capability inventory: The skill code in core/gif_builder.py and core/validators.py includes file system read/write operations (Pillow and imageio). It does not include network access, subprocess execution, or dynamic code evaluation. * 4. Sanitization: No explicit content sanitization or metadata stripping is implemented.
- [SAFE]: All identified dependencies (pillow, imageio, imageio-ffmpeg, numpy) are reputable, well-known libraries from standard registries.
- [SAFE]: No evidence of hardcoded credentials, network exfiltration, obfuscation, or unauthorized command execution was found across the skill files.
Audit Metadata