The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions and example projects reference standard software dependencies (such as Express, FastAPI, and Next.js) and the vendor-provided Hookdeck CLI for local development and testing. These are typical requirements for building and testing the provided webhook handler examples.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data in the form of Jira webhook payloads. This creates a surface for indirect prompt injection if the payload content (e.g., issue summaries or comments) is later passed to an LLM without sanitization.
Ingestion points: Webhook endpoints defined in examples/express/src/index.js, examples/nextjs/app/webhooks/jira/route.ts, and examples/fastapi/main.py ingest the raw HTTP request body.
Boundary markers: The skill implements cryptographic signature verification (X-Hub-Signature) to authenticate the source of the data, which is a robust security measure, though it does not inspect the content for prompt injection patterns.
Capability inventory: The provided examples primarily log payload data to the console and provide placeholders for syncing data to external systems or triggering notifications.
Sanitization: The skill provides logic for cryptographic validation but does not include specific sanitization or filtering for the natural language content within the payloads.

jira-webhooks