create-sticker
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary functionality is to generate and process images, which is performed using established libraries and official APIs. The code is transparent and lacks any obfuscation or hidden logic.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied pose descriptions and includes them in the prompt for the image generation model. While this constitutes an injection surface, it is inherent to the skill's purpose and the risk is contained within the image generation context.
- Ingestion points: User input via the command-line description argument in
scripts/create_sticker.py. - Boundary markers: User input is appended to a character base prompt without specific delimiters.
- Capability inventory: Includes image generation via the Google Gemini API and writing PNG files to the local
~/stickers/directory. - Sanitization: Input used for filenames is sanitized for shell safety, while the pose description is passed directly to the model as part of the visual generation prompt.
Audit Metadata