rocketlist
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to connect to an external Model Context Protocol (MCP) tool at
https://rocketlist.ai/mcpto perform job and company searches. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external job and company descriptions. It manages the risk of untrusted data by instructing the agent to verify every job via specific tool calls (
get_job/get_company), prohibiting the inference of information (like visa sponsorship or funding) not explicitly stated in the records, and requiring evidence for all results.
Audit Metadata