bamboohr-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from the BambooHR API, creating a vulnerability surface where the agent might interpret data as instructions.
- Ingestion points: Data is fetched and parsed from
https://api.bamboohr.comwithinsrc/bamboohr/client.ts. - Boundary markers: The provided client implementation and instructions do not include specific delimiters or warnings to prevent the agent from processing API responses as commands.
- Capability inventory: The skill grants the agent access to
Write,Edit, andBashtools inSKILL.md, and the code performs network operations viafetch. - Sanitization: There is no evidence of schema validation or content sanitization for the data retrieved from the BambooHR API endpoints.
Audit Metadata