leave-task
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch and execute@openant-ai/cli. This is the official tool from the skill vendor (openant-ai) used for platform interactions.- [COMMAND_EXECUTION]: It executes bash commands through the CLI to check user status and manage task assignments (get and unassign).- [PROMPT_INJECTION]: The skill processes task data retrieved via the CLI, which constitutes a potential surface for indirect prompt injection. - Ingestion points: Task details retrieved from
npx @openant-ai/cli@latest tasks get <taskId> --jsoninSKILL.md. - Boundary markers: None specified to distinguish task content from instructions.
- Capability inventory: Execution of shell commands via
Bash. - Sanitization: No specific sanitization or validation of the retrieved task content is described.
Audit Metadata