sanity-check
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run programs and scripts for sanity checks.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it instructs the agent to ingest data from external sources. * Ingestion points: Real data, API responses, and documentation are ingested from external environments. * Boundary markers: No specific delimiters are provided to distinguish data from instructions. * Capability inventory: The agent has access to the Bash tool for local command execution. * Sanitization: There is no requirement to sanitize or validate external content before processing.
Audit Metadata