svix-sending-webhooks
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes the user's codebase to identify configuration patterns, tenant identifiers, and event types to assist with integration. This ingestion of untrusted repository data constitutes an indirect prompt injection surface.\n
- Ingestion points: The skill uses
Read(./**)andGrep(./**)to inspect the local filesystem for manifest files, environment variables, and source code.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the processed repository files.\n
- Capability inventory: The skill is capable of generating integration plans (writing to
SVIX_PLAN.md) and prompting the user with questions based on its analysis.\n - Sanitization: There is no explicit logic described to sanitize or validate data extracted from the repository before presenting it to the user or incorporating it into a plan.
Audit Metadata