The Agent Skills Directory

[SAFE]: The skill acts as a documentation and implementation guide for Upstash QStash. Systematic review of the instructions and code snippets in SKILL.md and references/detailed-guide.md found no evidence of malicious behavior, obfuscation, or unauthorized system access.
[CREDENTIALS_UNSAFE]: The skill promotes secure development practices by explicitly instructing the use of environment variables (e.g., process.env.QSTASH_TOKEN) and warning against hardcoded secrets.
[INDIRECT_PROMPT_INJECTION]: The skill acknowledges the risks associated with processing external webhook data. 1. Ingestion points: Webhook endpoints consuming POST request bodies as described in references/detailed-guide.md. 2. Boundary markers: Clear instructions to treat endpoints as public and perform mandatory signature verification. 3. Capability inventory: Messaging, scheduling, and URL group management via the @upstash/qstash SDK. 4. Sanitization: Implementation of signature verification using the Receiver class and recommendations for schema and idempotency validation.

upstash-qstash