byted-recruitment-bosszhipin
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by reading candidate profiles and resumes from the BOSS Zhipin recruitment platform. 1. Ingestion points: Candidate data fetched via the browser from the zhipin.com website. 2. Boundary markers: The instructions do not specify delimiters or warnings to ignore instructions that might be embedded in candidate resumes or profiles. 3. Capability inventory: The skill uses browser interaction, local file reading, and local file writing within the workspace. 4. Sanitization: No specific sanitization or filtering of the external text is described before it is used for scoring or storage.
- [COMMAND_EXECUTION]: The skill executes JavaScript within the browser context to handle page scrolling. Evidence: The instruction
browser action=act kind=evaluate fn="window.scrollBy(0, 1000)"is used to load additional candidate records.
Audit Metadata