baoyu-xhs-images
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documentation in
references/codex-imagegen.mddescribes a fallback mechanism usingnpx -y bunto execute local scripts if the Bun runtime is not found on the system. This involves downloading the tool from the npm registry. - [DYNAMIC_EXECUTION]: The skill dynamically discovers and executes local scripts or binaries, such as those specified by the
BAOYU_CODEX_IMAGEGEN_BINenvironment variable or found within the skill's package structure (e.g.,packages/baoyu-codex-imagegen/src/main.ts). - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided content to generate image prompts. While it lacks explicit sanitization or boundary markers, the risk is low as the primary output is static images. Evidence: 1. Ingestion points:
SKILL.mdStep 1 andanalysis-framework.md. 2. Boundary markers: Absent. 3. Capability inventory:Skilltool calls, file writing, and script execution. 4. Sanitization: Absent.
Audit Metadata