Back to skill

Security audit

Am I going in circles?

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local workflow helper for detecting repeated tool use, with no artifact evidence of hidden execution, exfiltration, or destructive behavior.

Before installing, be aware that this skill asks the agent to install and enable the ClawPhylax plugin, which keeps a local ledger of request and tool-outcome history for repetition checks. That behavior is disclosed and purpose-aligned, but users who do not want local session activity recorded should avoid enabling the plugin.

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
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
93% confidence
Finding

The description says to use the skill when "something feels familiar" or when "progress stalls," which are subjective conditions without clear boundaries. These broad cues can cause unintended invocation because they overlap with many ordinary troubleshooting situations and do not define when the skill should not be used beyond one narrow exception.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrases "I have done this before" and "no progress for several calls" are imprecise and rely on subjective judgment. Because the section does not define measurable thresholds for several of these cases, the activation scope remains ambiguous and may lead to overuse.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.