workhuman-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from traffic logs (using
Read,Glob,Grep) and external vendor documentation (viaWebFetch) to generate control policies and configuration files (Write,Edit). - Ingestion points: Traffic logs, retry configuration files, and external Workhuman documentation fetched via the
WebFetchtool. - Boundary markers: The instructions lack explicit delimiters or specific warnings to ignore instructions that may be embedded in the external content (e.g., within traffic logs or documentation).
- Capability inventory: The skill utilizes
WriteandEdittools to create or modify system controls, models, and fixtures based on the analyzed data. - Sanitization: No sanitization or validation logic is defined for the external data before it is processed or used in file-writing operations.
Audit Metadata