ClawHub
Back to skill

Security audit

seo-drift

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SEO monitoring helper that fetches user-specified pages and stores local comparison history, with no artifact-backed evidence of hidden or malicious behavior.

Install this if you want an agent to monitor SEO changes for URLs you provide. Be aware it will fetch those pages and keep local baseline/history data in a SQLite cache, so avoid using it for pages whose SEO metadata or fetched content should not be retained locally.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises broad trigger phrases such as 'baseline', 'track changes', 'before and after', and 'deployment check', which can match ordinary user requests outside the intended SEO context. This can cause unintended auto-invocation of the skill, leading the agent to fetch external URLs, read/write local state, or steer the conversation into actions the user did not explicitly request.

Content

No source excerpt is available for this finding.

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md
(blocks private IPs, loopback, reserved ranges, GCP metadata endpoints)
- **No curl, no subprocess HTTP calls** -- only the project's validated fetch pipeline
- **All SQLite queries** use parameterized placeholders (`?`), never string interpolation
- **TLS always verified** -- no `verify=False` anywhere in the pipeline

---

Static analysis

No suspicious patterns detected.