ClawHub
Back to skill

Security audit

pressure-test

Security checks for vulnerabilities and agentic risk

Overview

This planning skill provides transparent, bounded autonomous decision-making and records its reasoning for user review.

Specify which planning task autonomous mode applies to, review decisions labeled judgment, and expect a decision transcript to be saved alongside the 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
  • 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)

Sous-mode triggers include everyday handoff phrases without requiring an active pressure-testing task.

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding

Phrases such as "figure it out" and "I'm going AFK" occur in many unrelated workflows, but this activation rule does not explicitly restrict them to an ongoing pressure-test session. The description at line 5 repeats these broad handoff conditions, potentially invoking autonomous planning when the user merely delegates another task or announces an absence.

Content

No source excerpt is available for this finding.