cloud-arch
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a local script
python3 scripts/cache_docs.pyto fetch and manage document caches. The command uses a permalink argument derived from a provided mapping table. - [EXTERNAL_DOWNLOADS]: The skill's caching workflow downloads documentation from the vendor's official domain (
jeesite.com). This is documented as a standard operation for the author's services. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing external markdown files.
- Ingestion points: Documentation is downloaded from
jeesite.comand stored inreferences/.cache/cloud-arch/or~/.cache/jeesite/cloud-arch/. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and the ingested document content.
- Capability inventory: The skill utilizes a local Python script for network retrieval and file system writes within the cache directory.
- Sanitization: There is no evidence of validation or sanitization of the external content before it is read by the agent.
Audit Metadata