anime-soccer
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains highly specific and directive instructions (e.g., "The proven pipeline (do not deviate from the order)", "The formula is mandatory") aimed at guiding the agent's creative process and ensuring output consistency. These are legitimate instructional constraints rather than malicious overrides.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted user data (photo, name, team details) and interpolates it into prompts for image and video generation tools.
- Ingestion points: User inputs are collected in "Stage 0" and used in the prompts for
generate_image_editandgenerate_reference_video(e.g.,{NAME},{HERO}). - Boundary markers: The skill does not employ delimiters or explicit instructions to the generative models to ignore potential commands embedded within the user-supplied strings.
- Capability inventory: The skill has access to image/video generation, asset uploading, and file concatenation tools within the Pika MCP environment.
- Sanitization: There is no evidence of sanitization or validation logic for the user-provided text inputs before they are interpolated into the final prompts.
Audit Metadata