ClawHub
Back to skill

Security audit

Intelligent Continuous Requirements Analysis v4

Security checks for vulnerabilities and agentic risk

Overview

This is a legitimate requirements-analysis guide, but it needs review because it encourages AI analysis of customer logs and ongoing user-behavior monitoring without clear privacy safeguards.

Install only if you are comfortable applying it to requirements work with your own privacy controls. Before using it on real customer feedback, support logs, production monitoring, or behavior analytics, require approval, remove personal data and secrets, minimize fields, document retention and access, and avoid sending sensitive telemetry to external AI services unless authorized.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly recommends automated analysis of user feedback, customer service logs, app-store reviews, and similar operational data, but it does not require privacy review, consent checks, minimization, redaction, or handling rules for potentially sensitive personal data. In a requirements-engineering skill, this omission can normalize ingestion of production/user data into AI workflows, creating privacy, compliance, and inadvertent data-exposure risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The continuous feedback loop instructs automatic collection and analysis of monitoring and user-behavior data, yet provides no warning about privacy implications, production telemetry sensitivity, or potential operational impact of instrumentation. Because this is framed as an always-on process, it increases the chance of persistent over-collection, unauthorized profiling, or routing sensitive telemetry into AI systems without review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

SQP-3 covers natural-language policy violations such as forcing a specific language without user opt-in. Although some English terms appear, the substantive instructions and examples are presented in Chinese only, with no indication that users may choose another language or that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.