character-candid-photography
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (character names and descriptions) and interpolates it into the final generated image prompts, creating a surface for injection.
- Ingestion points: The skill accepts a
{角色}(character) variable and additional user-specified parameters (style, location, action) as seen inreferences/photography-guide.mdandSKILL.md. - Boundary markers: The skill lacks explicit boundary markers or instructions to the model to ignore potentially malicious commands embedded within the user-supplied character descriptions.
- Capability inventory: The skill's capabilities are limited to text generation; it does not have access to tools for file system modification, network communication, or command execution.
- Sanitization: There is no evidence of input validation or sanitization to filter out prompt injection attempts from the user-provided data.
Audit Metadata