extend-fun
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script,
scripts/cache_docs.py, to manage the downloading and caching of documentation files. - [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of documentation from
https://jeesite.com, which is the official website for the framework associated with the skill's author, thinkgem. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes content from external web sources.
- Ingestion points: Document content is stored in
references/.cache/extend-fun/and read by the agent to answer queries. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched documents.
- Capability inventory: The skill has the capability to execute local scripts and read/write to the filesystem.
- Sanitization: There are no mentioned mechanisms for sanitizing or filtering the content fetched from the external documentation site.
Audit Metadata