omni-webhooks
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Employs the
curlcommand-line tool to perform HTTP requests against a local service athttp://localhost:20128. - [INDIRECT_PROMPT_INJECTION]: The skill manages webhook registrations and delivery monitoring, which represents a surface for untrusted data to enter the agent's context.
- Ingestion points: Webhook endpoint registration and delivery history retrieval defined in
SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation.
- Capability inventory: The skill is limited to CRUD operations on the local API using
curl. - Sanitization: There is no mention of sanitization or validation processes for external webhook payloads.
Audit Metadata