oulang-bq-to-notion

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: 0.90). The skill explicitly instructs agents to capture "credentials/endpoints/service accounts" as durable Notion findings and provides an auth pattern (printing an access token then using it in a curl) which could lead the LLM to embed access tokens or secret values verbatim into generated commands or Notion entries, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 0.90). High risk: the skill mandates use of a hard-coded, highly privileged service account and shows how to extract its access token, and it requires persisting query results — including credentials/endpoints/service-account information — to an external Notion workspace, which creates a straightforward data-exfiltration and credential-theft pathway.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to "notion-fetch" topic pages at runtime and to skip or alter actions if the fetched page already contains the fact (e.g., https://api.notion.com/v1/pages/3402ea9b77ad81b5aefaf0e86e954ab3), so external Notion content would directly control the agent's behavior.

Issues (3)

W007
HIGH

Insecure credential handling detected in skill instructions.

E006
CRITICAL

Malicious code pattern detected in skill scripts.

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Apr 14, 2026, 09:37 AM
Issues
3