castai-webhooks-events
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a TypeScript implementation for a webhook receiver that ingests data from external sources.
- Ingestion points: The
app.post("/castai/events", ...)endpoint incastai-webhook-handler.tsprocesses incoming HTTP POST request bodies (req.body). - Boundary markers: The code does not implement any delimiters or instructions to treat the incoming payload as untrusted data.
- Capability inventory: The skill is capable of logging data to standard output and making external network requests to a Slack webhook via
fetch. - Sanitization: No input validation or escaping is applied to the event data before it is logged or transmitted to external services.
- [COMMAND_EXECUTION]: The skill instructions provide shell commands using
curlto query the CAST AI audit log and define a KubernetesCronJobthat uses a shell script to fetch savings data. These are standard operations for the described use case and utilize environment variables for authentication. - [EXTERNAL_DOWNLOADS]: The skill references and fetches the official CAST AI OpenAPI specification from
api.cast.ai. This is a well-known service related to the skill's primary purpose.
Audit Metadata