frontend-beetl
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/cache_docs.pyto manage documentation retrieval. This script is called with arguments derived from a predefined mapping table. - [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from
jeesite.com. This domain is the official resource for the framework documentation described in the skill. - [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection by ingesting and processing content from external documentation files.
- Ingestion points: Markdown documentation files are cached in
references/.cache/frontend-beetl/or~/.cache/jeesite/frontend-beetl/after being fetched from the web. - Boundary markers: The skill lacks explicit instructions or delimiters to tell the agent to ignore any malicious instructions that might be embedded within the retrieved documentation.
- Capability inventory: The skill includes the ability to execute shell commands (via the Python interpreter).
- Sanitization: There is no specified sanitization or content filtering for the data read from the external documentation files.
Audit Metadata