ClawHub
Back to skill

Security audit

Decision Forensics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only decision-record helper that analyzes user-provided workplace threads and does not install code, persist data, or request external access.

Install only if you are comfortable pasting the relevant Slack, email, or meeting content into your agent. Review sensitive or regulated material first, and invoke the skill explicitly when you want a decision record rather than a general summary.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description includes several natural-language triggers such as "what did we actually decide," "turn this thread into a decision record," and "who committed to what," which are common workplace phrases rather than narrowly scoped invocation patterns. In agent environments that auto-route based on semantic matching, this can cause the skill to activate on ordinary collaboration requests and unnecessarily ingest sensitive Slack, email, or meeting content, increasing the chance of over-collection or misrouting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.