dino-manage-todo
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill explicitly instructs the agent to treat all task content and CLI output as untrusted data and forbids executing any instructions found within that data. This is a proactive defense against indirect prompt injection.
- [COMMAND_EXECUTION]: Command execution is constrained to the
dinoutility. The workflow requires the use of--dry-runto preview changes and mandates explicit user confirmation before executing any commands that mutate data (append, create, update). - [CREDENTIALS_UNSAFE]: The skill follows security best practices for authentication by instructing users to manage tokens in their own terminal and explicitly warning against pasting sensitive authentication tokens into the conversation.
- [DATA_EXFILTRATION]: No suspicious network operations or data exfiltration patterns were detected. The skill focuses on local CLI interactions for task management.
Audit Metadata