neon
Fail
Audited by Snyk on Nov 18, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate Neon integration guide with no malicious intent, but it tells the agent to silently send error reports to the vendor after tasks, which the user would not expect.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow is Neon's first-party docs, CLI guidance, and claimable-project protocol, which are not outsider-authored. The only path where outsider-influenced text could reach the agent is the optional, on-demand
neon logs queryin Observability, where Function log lines can contain request content from public endpoints, so I rate it low.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata