character-and-continuity

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external character 'bibles' to generate image prompts. It mitigates potential injection risks through explicit validation rules, including prohibitions on digits, celebrity names, and terms referring to minors. It uses a multi-stage casting gate to ensure outputs align with these safety constraints.
  • [DATA_EXPOSURE]: The skill uses localized file paths (e.g., cast/<id>/, projects/<id>/continuity/) to store character assets and continuity records. These paths are specific to the creative workflow and do not access sensitive system directories, credentials, or environment variables.
  • [COMMAND_EXECUTION]: The instructions reference internal scripts for casting and validation (src/crafts/narrative/casting.ts, src/crafts/narrative/gate.ts). There are no patterns suggesting the execution of arbitrary shell commands or the fetching of remote scripts from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 11:41 PM