ClawHub
Back to skill

Security audit

Complianceradar Ai Monitor

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent, but it asks users to connect sensitive compliance workflows to several external services with limited control and privacy detail.

Review this before installing in a regulated environment. Use dedicated least-privilege API keys and webhooks, avoid sending confidential customer or legal strategy data into prompts unless approved, and require human review before external notifications, task creation, policy updates, or audit evidence publication.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 7)May include surrounding context.

md
ENAI_API_KEY"],"bins":["curl","jq"]},"os":["macos","linux","win32"],"files":["SKILL.md"],"emoji":"📋"}}

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation states that API keys are 'never logged or transmitted to third parties,' yet the skill explicitly depends on OpenAI for impact assessment, which necessarily involves sending regulatory text and potentially organizational context to an external processor. This is a material privacy/security misrepresentation that can cause operators to handle sensitive compliance data under false assumptions, increasing legal, contractual, and data-governance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 320)May include surrounding context.

Solution: FDA API may have delayed indexing (up to 24 hours). Try:

bash
# Check API status
curl https://api.fda.gov/status.json

# Expand date range
Monitor FDA announcements from the last 30 days (not 7 days)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation states the skill 'currently monitors English-language documents only,' which is a language/locale constraint. Under the policy, forcing a specific language without user choice can be a natural-language policy violation, and this limitation is presented as fixed behavior rather than an opt-in setting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.