oodle-alerting

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the oodle CLI from the vendor's official Homebrew tap (oodle-ai/oodle/oodle). This is expected behavior for a tool-specific skill from the same author.
  • [COMMAND_EXECUTION]: The skill uses the oodle CLI to perform various management tasks including listing, creating, and deleting alerting configurations (notifiers, policies, and muting rules).
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes JSON output from discovery commands to perform subsequent operations.
  • Ingestion points: Output from commands like oodle notifiers list -o json and oodle monitors list -o json is ingested by the agent to resolve IDs.
  • Boundary markers: Absent; the skill does not use specific delimiters to isolate tool output.
  • Capability inventory: The skill possesses write and delete capabilities via the oodle CLI (create, update, delete).
  • Sanitization: No explicit sanitization or validation of the ingested JSON data is specified before its use in further commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 04:40 PM
Security Audit — agent-trust-hub — oodle-alerting