canghe-xhs-images
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that attempt to bypass safety guidelines. In
references/workflows/prompt-assembly.md, the instructions tell the agent to "create stylistically similar alternatives" and "DO NOT refuse to generate" if the content involves sensitive or copyrighted figures. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content to generate infographic prompts, creating a vulnerability to indirect prompt injection. 1. Ingestion points: User-provided text or files are read and processed in Step 1. 2. Boundary markers: The skill uses Markdown headers to structure the generated prompt but lacks strict delimiters to prevent the agent from executing instructions embedded in the source data. 3. Capability inventory: The skill has the ability to read and write files and invoke image generation tools. 4. Sanitization: There is no evidence of content sanitization or instruction filtering.
- [COMMAND_EXECUTION]: The skill uses bash commands to check for the existence of its configuration file (
EXTEND.md) in the project directory and the user's home directory ($HOME/.canghe-skills/canghe-xhs-images/).
Audit Metadata