ClawHub
Back to skill

Security audit

agent-analytics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed product-analytics helper that uses a pinned external CLI, browser approval, and scoped analytics workflows; its sensitive behaviors are purpose-aligned and bounded by consent and verification guidance.

Install only if you are comfortable using the Agent Analytics npm CLI and granting browser-approved access to your analytics account. Before setup, confirm the project goal and event plan, review any tracker/code changes, keep `.openclaw/agent-analytics/config.json` out of git, and avoid storing PII, secrets, or temporary analysis notes in project context.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/growth-recipes.md (reported line 31)May include surrounding context.

md
Use Bullseye for channel bets:

1. Outer ring: list plausible channels without judging too early.
2. Middle ring: select channels that can plausibly deliver activated users, not just signups.
3. Inner ring: run small tests with a defined input metric, activation metric, guardrail, and stopping rule.

Static analysis

No suspicious patterns detected.