ClawHub
Back to skill

Security audit

DocsForAI

Security checks for vulnerabilities and agentic risk

Overview

This skill behaves like a documentation crawler and its network access and persistent local files are disclosed and aligned with that purpose.

Install only if you are comfortable with the agent fetching documentation websites you request, storing those docs locally, and recording downloaded sites in MEMORY.md. Prefer the uv install path and avoid the pip --break-system-packages fallback unless you understand the system Python impact.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs crawling external sites and storing persistent files on disk without requiring user awareness or confirmation of the resulting network access and local writes. In an agent environment, this can lead to unexpected external requests, retention of third-party content, and accumulation of local artifacts the user did not explicitly approve.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instructions require appending to `MEMORY.md`, a persistent local file, without warning the user that the skill modifies local state outside the downloaded docs themselves. Silent edits to memory or tracking files can create integrity and privacy issues, especially if users do not expect the skill to maintain long-lived records of accessed sites.

Static analysis

No suspicious patterns detected.