ClawHub
Back to skill

Security audit

scent-trails

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable design-pattern skill for anonymous, decaying coordination signals, with broad wording but clear privacy limits and no hidden code or external actions.

Before installing, treat this as a conceptual coordination/privacy pattern. Any real implementation should preserve the stated limits: coarse disclosed cells, no person-shaped identifiers, no logs or user-content summaries, local or in-memory state by default, bounded decay, and human-confirmed export only. Consider tightening trigger examples if accidental invocation in ordinary privacy or collaboration discussions would be disruptive.

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
93% confidence
Finding

Because this is a markdown file, vague-trigger review applies. The description says the skill should be used when 'designing or operating shared fields where many intelligences coordinate and surveillance is unacceptable,' which is conceptual and very broad rather than giving specific invocation phrases, contexts, or exclusions tied to actual use conditions. That ambiguity could cause unintended invocation in many ordinary collaboration or privacy-related situations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.