c-tasks
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local CLI tools (
todoist-cli,things-cli, andtask) to manage tasks. It executes these tools via subprocess calls to perform listing, adding, and completing tasks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external task managers that could be controlled by an attacker.
- Ingestion points: Data is ingested from the output of task listing commands (e.g.,
todoist-cli list,task list), which includes user-generated task names and project descriptions. - Boundary markers: There are no markers or instructions used to separate retrieved task data from the agent's core instructions.
- Capability inventory: The agent has the ability to execute further shell commands to modify, delete, or add tasks based on the ingested data.
- Sanitization: There is no evidence of sanitization or filtering of the retrieved task content to prevent the agent from interpreting embedded instructions as commands.
Audit Metadata