dzen
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of a local Python script (
scripts/publish.py) to manage media uploads and content publication. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data into its workflow. 1. Ingestion points: The
--titleand--textcommand-line arguments inscripts/publish.pywhich receive content intended for publication. 2. Boundary markers: The script wraps text content in HTML<p>tags but lacks explicit delimiters or instructions to the model to ignore potential commands embedded in the input data. 3. Capability inventory: The skill has the capability to perform authenticated network POST requests tohttps://dzen.ruusing the user's session cookies. 4. Sanitization: No input validation or escaping is performed on the provided text strings before they are included in the API payload.
Audit Metadata