director-gate-check
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute a shell script at 'tools/scripts/gate-check.sh' as part of its primary workflow.\n- [INDIRECT_PROMPT_INJECTION]: The skill performs evaluations on external project data, which introduces a potential surface for indirect prompt injection.\n
- Ingestion points: Project assets, asset manifests, and visual/audio content from the active motion graphics project are processed.\n
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed data.\n
- Capability inventory: The skill possesses the capability to execute shell scripts ('gate-check.sh') in the local environment.\n
- Sanitization: There is no evidence of sanitization or validation of project content before it is used to influence the gate evaluation results.
Audit Metadata