oodle-monitors
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
oodleCLI tool via Homebrew from the vendor's official tap (oodle-ai/oodle/oodle). This is a legitimate installation of a vendor-owned tool. - [COMMAND_EXECUTION]: The skill uses the
oodleCLI to perform CRUD operations on monitors. Security is addressed through instructions that mandate resource discovery (listing before deleting) and user confirmation for ambiguous or high-impact actions. - [PROMPT_INJECTION]: The skill processes monitor configurations and alert messages which represents a potential surface for indirect prompt injection from externally-controlled data.
- Ingestion points: Monitor definitions retrieved via
oodle monitors listandoodle monitors get. - Boundary markers: Discovery and verification steps are advised to prevent unintended command execution.
- Capability inventory: Shell command execution via the
oodleCLI. - Sanitization: Not explicitly implemented, but the skill relies on manual review and confirmation protocols.
Audit Metadata