architect-create-webhook-tool
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and act upon untrusted data to configure platform tools, creating a vulnerability surface where malicious instructions could be embedded in external data.
- Ingestion points: User-supplied API endpoints, authentication details, request/response schemas, and external documentation (SKILL.md, Section 1).
- Boundary markers: The instructions lack explicit boundary markers or directives to ignore embedded instructions within the ingested API data.
- Capability inventory: The agent is authorized to perform network requests to the ElevenLabs API, including creating new tools (POST /v1/convai/tools) and modifying agent configurations (PATCH /v1/convai/agents).
- Sanitization: No specific sanitization or validation steps are provided for the agent to perform on the external input before it is used to build API request payloads.
Audit Metadata