anima-prompt-crafter
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation and model resources hosted on Hugging Face (huggingface.co/circlestone-labs/Anima) and the Comfy Org tutorial site. These represent well-known, trusted organizations within the AI development community and are used solely for reference.
- [COMMAND_EXECUTION]: The skill includes a local utility script,
scripts/validate_anima_prompt.py, which is intended to be executed by the agent to verify the format of generated prompt files. The instructions inSKILL.mdprovide a standard command line for running this checker using the local Python interpreter. - [PROMPT_INJECTION]: The skill is designed to process untrusted user input, such as creative briefs and character descriptions, to generate refined image prompts. This introduces an indirect prompt injection surface where malicious instructions in the user's input could attempt to influence the behavior of the image generation pipeline.
- Ingestion points: User briefs, character notes, and style references are ingested into the prompt generation workflow as described in
SKILL.mdandREADME.md. - Boundary markers: The skill uses labeled text blocks (e.g., 'Positive prompt', 'Negative prompt') but does not implement explicit boundary markers or instructions to ignore embedded commands within the user-provided data.
- Capability inventory: The skill allows for local file validation via shell command execution of its own validation script.
- Sanitization: No specific sanitization or filtering logic is documented for the user-supplied content before it is interpolated into the final prompt output.
Audit Metadata