laohan-fengmianqiuzhi
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from local video scripts, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads 01-口播稿.md to extract video titles and visual keywords.
- Boundary markers: The skill lacks explicit delimiters or instructions to prevent the agent from executing commands that might be embedded within the script text.
- Capability inventory: The agent is instructed to call an external image generation tool and write multiple files to the local file system based on the processed content.
- Sanitization: There is no evidence of input validation, escaping, or filtering of the script content before it is interpolated into the final image generation prompts.
Audit Metadata