gjc-sdk-discover
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
gjccommand-line tool to perform session discovery and inspection tasks. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from session transcripts and goals which could contain malicious instructions designed to influence the agent.
- Ingestion points: Data retrieved from
gjc sdk session inspectandgjc sdk session raw querycommands, includingtranscript.bodyandgoal.listinSKILL.md. - Boundary markers: No explicit delimiters or boundary warnings are specified for the ingested content.
- Capability inventory: The agent has the capability to execute shell commands using the
gjcCLI. - Sanitization: The skill mandates that only redacted JSON output be rendered and that CLI error streams be discarded.
Audit Metadata