ClawHub
Back to skill

Security audit

agent-bom discover snowflake

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Snowflake inventory workflow that uses operator-controlled read-only credentials and local output, with no evidence of hidden persistence, destructive actions, or exfiltration.

Install only if you intend to let the agent inventory your Snowflake environment. Use a read-only Snowflake role, verify the output path before running, and avoid exposing password, token, passphrase, or private-key contents in chat.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- python
      env: []
      credentials: snowflake-read-only
    credential_policy: "Use the operator's existing Snowflake SSO, OAuth, or key-pair auth context. Prefer SNOWFLAKE_PRIVATE_KEY_PATH or SNOWFLAKE_AUTHENTICATOR over SNOWFLAKE_PASSWORD. Do not ask users to paste passwords, private keys, or OAuth tokens into chat."
    optional_env:
      - SNOWFLAKE_ACCOUNT
      - SNOWFLAKE_USER
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.