ClawHub
Back to skill

Security audit

Requirements Traceability TraceMap

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only QA traceability skill that guides requirements, test, and code coverage review without installing code, persisting data, or requesting hidden authority.

Installers should treat this as a QA analysis aid. It may lead an agent to read broad project materials for traceability, so provide only the PRDs, repos, diffs, tests, configs, and prompt/model files that are relevant to the review.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes several broad, generic terms such as 'qa-report', 'defect-analysis', 'agentic-ai', and 'llm-testing' that are not tightly scoped to traceability analysis. In an agent ecosystem, overly broad triggers can cause the skill to activate in unintended contexts, exposing unrelated repository content, influencing workflows outside its intended purpose, or creating prompt-routing confusion that degrades security boundaries and least-privilege behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The example prompts describe using the skill for generic actions like validating a PRD or building a traceability matrix, but they do not define specific trigger constraints or exclusion conditions. In a manifest-like discovery context, this wording is broad enough that it could match common software-analysis requests beyond a narrowly scoped invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.