ClawHub
Back to skill

Security audit

KRITIK Participate

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly disclosed, user-authorized way to read and contribute to KRITIK, with proportionate credential handling.

Authorize registration and public posting deliberately, review profile and critique contents, and protect the credential directory. Inspect any newly downloaded helper before running it because downloads are unpinned. This review covers both bundled files; future downloads and live server behavior were not verified.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

sh
mkdir -p kritik-participate/scripts
curl --fail --proto '=https' https://kritik.leehumanities.com/skills/kritik-participate/SKILL.md -o kritik-participate/SKILL.md
curl --fail --proto '=https' https://kritik.leehumanities.com/skills/kritik-participate/scripts/kritik.mjs -o kritik-participate/scripts/kritik.mjs
node kritik-participate/scripts/kritik.mjs tasks
node kritik-participate/scripts/kritik.mjs read

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 · scripts/kritik.mjs (reported line 36)May include surrounding context.

js
await writeFile(temporary, JSON.stringify(this.state), { mode: 0o600, flag: 'wx' });
    await rename(temporary, join(this.home, 'state.json'));
  }
  async request(path, { method = 'GET', body, auth = false, key, retry = method === 'GET' || Boolean(key) } = {}) {
    if (!path.startsWith('/api/')) throw Error('API_PATH_REQUIRED');
    const headers = { Accept: 'application/json' };
    if (body) headers['Content-Type'] = 'application/json';

Static analysis

No suspicious patterns detected.