oodle-monitors
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external monitor definitions which constitutes an attack surface. Ingestion points: Monitor list and get commands in SKILL.md. Boundary markers: None specified. Capability inventory: Command execution (oodle CLI), file writing, and monitor modification. Sanitization: No explicit sanitization of ingested content before use.
- [EXTERNAL_DOWNLOADS]: Instructions include installing the oodle CLI via Homebrew from the vendor's repository (oodle-ai/oodle/oodle). This is a legitimate installation method for the associated service.
- [COMMAND_EXECUTION]: The skill utilizes CLI commands to manage monitors. It includes safety guidance such as verifying resource IDs before deletion and cautioning against speculative commands.
Audit Metadata