character-design-continuity
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, command execution, or obfuscation techniques were identified in the provided files. The skill functions as a set of instructional guidelines for character design workflows.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override system prompts or bypass safety guidelines. On the contrary, the skill explicitly warns the agent to pause for consent and legal review when dealing with real-person likenesses or licensed IP, reinforcing safety protocols.
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs to reputable organizations (e.g., copyright.gov, sagaftra.org, waltdisney.org) and academic research papers (e.g., arXiv.org). These are provided solely for educational reference and do not involve the automated downloading or execution of untrusted scripts.
- [INDIRECT_PROMPT_INJECTION]: While the skill involves processing user-provided character descriptions and images, it provides structured methods (such as the character bible and continuity ledger) to handle this data safely. It does not utilize dynamic shell execution or other high-risk capabilities that would be susceptible to injection attacks.
Audit Metadata