planetscale-webhook-automation-recommendations
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes automation workflows where an agent ingests data from external PlanetScale webhook events (such as branch anomalies, schema recommendations, or deploy request events). This ingestion represents a potential attack surface where malicious content within the external event payload could attempt to influence the agent's logic.
- Ingestion points: External PlanetScale webhook event payloads (SKILL.md, 'Events to evaluate' section).
- Boundary markers: The skill explicitly requires human review gates for production-affecting work and mandates the use of review-protected branches.
- Capability inventory: The recommended workflows assume the agent has the capability to create development branches, open pull requests, and generate triage reports or issues.
- Sanitization: The skill includes mandatory security requirements for webhook receivers, including HTTPS, signature verification using secrets, and idempotency checks.
Audit Metadata