ClawHub
Back to skill

Security audit

software-requirements-engineering-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-focused requirements engineering skill with no executable code, install hooks, hidden persistence, or unrelated data-handling behavior found.

Install this skill when you want structured help creating or reviewing software requirements. It may ask to read project documents you provide, so keep sensitive or unrelated files out of scope unless they are needed for the requirements work.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/srs.md (reported line 173)May include surrounding context.

md
- compound statements that hide multiple requirements
- negative requirements when positive behavior is clearer
- design choices unless they are real constraints
- open-ended lists such as "including but not limited to" without bounds

## Functional Requirements

Static analysis

No suspicious patterns detected.