cancel-task
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and executes the
@openant-ai/clipackage from the NPM registry vianpxto perform platform operations. - [COMMAND_EXECUTION]: Utilizes system shell commands to invoke the vendor CLI for task status verification, cancellation, and settlement checks.
- [PROMPT_INJECTION]: The skill ingests untrusted task data (such as titles and descriptions) from the OpenAnt platform, creating a vulnerability to indirect prompt injection.
- Ingestion points: Task metadata retrieved using the
tasks getcommand in SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the task data fields.
- Capability inventory: The agent has the ability to cancel tasks and verify financial settlements.
- Sanitization: No sanitization or validation logic is specified for the data returned from the platform before it is processed by the agent.
Audit Metadata