ClawHub
Back to skill

Security audit

AIScope Setup

Security checks for vulnerabilities and agentic risk

Overview

This setup skill is clear about installing AIScope, verifying it, and running a limited first scan, with reasonable user-control instructions.

Before installing, prefer the checksum-verified release or pinned `aiscope-cli@0.1.2` package paths. If using the standalone skill command, be aware that the `skills` CLI package is not version-pinned, so review or pin that installer if your environment has strict supply-chain requirements.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill instructs use of npx --yes skills without pinning a specific package version, which allows whatever version is current in the registry at execution time to run code on the user's machine. Because npx fetches and executes remote package code, a compromised upstream package, malicious publish, or breaking change could lead to arbitrary code execution or unsafe behavior during setup.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

npx --yes skills add Jayanth-MKV/aiscope --skill aiscope-setup aiscope --agent codex --copy --yes

text

Replace `codex` with the current agent's identifier. Default to project scope; use `--global` only if the user requests it. If Node.js is unavailable, copy just the two skill directories from the repository's `skills/` folder to the current agent's supported skills directory. Do not overwrite an existing skill without checking it. A plugin already supplies both skills, so skip a duplicate standalone installation.

Verify with `aiscope --version`, then run `aiscope --specific --json .` from the target project. Parse stdout as JSON and confirm its `root` matches the intended directory. Do not launch the TUI or watch mode during setup. Explain scan coverage and any returned conflicts; leave instruction files unchanged unless changes were requested. User-wide instructions require the explicit `--user` opt-in.

Static analysis

No suspicious patterns detected.