ClawHub
Back to skill

Security audit

soft-agent-module

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for acore-agent development, with one overbroad activation trigger that users should narrow but no evidence of hidden execution or data access.

Install only if you work on the acore-agent module. Consider narrowing the trigger terms to acore-agent, Dify Agent, DeerFlow Agent, or specific class names so it does not activate for unrelated agent discussions.

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

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs activation on extremely generic terms like 'Agent', 'agent', and even broad module references, which can cause the skill to trigger in many unrelated conversations. Over-broad auto-activation increases the chance of irrelevant context injection, user confusion, and unsafe privilege expansion where the agent module guidance is surfaced outside its intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.