lov-add-task
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted task descriptions and existing task list files, creating a surface where malicious instructions embedded in a task could potentially influence the agent's behavior.
- Ingestion points: User-supplied task descriptions and existing task list files referenced in the
SKILL.mdworkflow. - Boundary markers: The workflow does not explicitly define markers or 'ignore' instructions to isolate processed data from the agent's execution logic.
- Capability inventory: The skill has the capability to modify local files to update the task list (defined in
SKILL.md). - Sanitization: No explicit validation or sanitization of the input task content is specified.
Audit Metadata