canghe-comic
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content to generate storyboards and image generation prompts, creating a surface for indirect prompt injection.
- Ingestion points: Source content is read from user-provided files or pasted text as described in Step 1.2 of the workflow.
- Boundary markers: The skill does not use explicit delimiters or instructions to isolate user content from the agent's internal logic during the analysis phase.
- Capability inventory: The skill has the capability to execute local scripts and interact with external image generation tools.
- Sanitization: No sanitization or validation of the user-provided content is performed before it is incorporated into the prompt generation pipeline.
- [COMMAND_EXECUTION]: The skill executes local TypeScript scripts using the bun runtime via npx.
- Evidence: The workflow involves calling npx -y bun to execute the merge-to-pdf.ts script and a main.ts script located in a sibling skill directory.
- [PERSISTENCE]: The skill maintains user preferences across sessions by storing a configuration file in a hidden directory within the user's home folder.
- Evidence: Preferences are saved to the .canghe-skills/canghe-comic/EXTEND.md file in the user's home directory ($HOME).
Audit Metadata