baoyu-xhs-images

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands such as test, echo, and mkdir to manage configuration files and directory structures. These operations are restricted to the local project directory and a specific sub-folder in the user's home directory ($HOME/.baoyu-skills/).
  • [COMMAND_EXECUTION]: The skill executes a local script located at ${SKILL_DIR}/scripts/main.ts using the bun runtime, which is invoked via npx during the image generation phase.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the npx utility, which may download dependencies from the official npm registry, a well-known and trusted service, to facilitate script execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user content to generate infographic prompts. It employs structured templates, frontmatter, and explicit section headers (e.g., ## Content) to maintain clear boundaries and reduce the risk of the agent misinterpreting data as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 02:09 AM