groq-webhooks-events
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (webhooks, batch prompts) which represents a surface for indirect prompt injection where malicious data could influence the LLM's classification logic.
- Ingestion points:
processWebhookEvent(references/implementation.md),submitBatch(references/implementation.md), and the SSE endpoint (SKILL.md) all ingest data from external requests. - Boundary markers: The prompts in
processWebhookEventlack specific delimiters or instructions to ignore embedded commands within theeventJSON payload. - Capability inventory: The skill uses
fetchto send data to callback URLs and interacts with Slack notifications, which could be triggered by injected payloads processed by the LLM. - Sanitization: There is no evidence of sanitization or validation of the input data before it is interpolated into the LLM prompts.
Audit Metadata