laohan-shencha
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data including technical documentation, scripts, and oral scripts.
- Ingestion points: Processes technical scripts (.py, .sh, .ps1), configuration files, and oral scripts like
01-口播稿.md. - Boundary markers: The skill does not define specific delimiters or boundary markers to isolate untrusted content from agent instructions during the verification process.
- Capability inventory: The skill uses
curl,gh,npm,pip, anddockerfor verification and has file-writing capabilities when inVERIFY_AND_FIXmode. - Sanitization: There is no evidence of specific sanitization or filtering of the processed content.
- [COMMAND_EXECUTION]: The skill instructions specify the use of several command-line utilities to perform its verification purpose.
- Evidence: Mentions using
gh repo view,gh api,npm view,pip index,brew info, andcurlto check for resource availability and metadata. - [EXTERNAL_DOWNLOADS]: The skill fetches data from multiple external sources to verify claims.
- Evidence: Communicates with official APIs and repositories for GitHub, NPM, PyPI, Docker Hub, and HuggingFace, as well as general web search services. These are well-known technology services and are used according to the skill's primary function.
Audit Metadata