oulang-data-query
Fail
Audited by Snyk on Apr 14, 2026
Risk Level: CRITICAL
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to retrieve sensitive secrets (PRIVATE_KEY, POSTHOG_API_KEY, MYSQL_CONNECTION_STRING, etc.) from agent memory or env and embed them verbatim into JWT construction and curl/request payloads, forcing the LLM to handle and output secret values directly.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.95). This skill includes high-risk data-exfiltration and credential-exposure patterns (sending DB connection strings, PostHog API keys, and requesting a service-account PRIVATE_KEY) to third-party proxies/endpoints (e.g., cors.trigox.workers.dev, posthog.pime.ai/infohuaxin.es), which enables unauthorized access to sensitive user/payment data and secrets.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
Audit Metadata