ClawHub
Back to skill

Security audit

reconcile

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only repository reconciliation helper that fits its stated purpose, with the main caveat that its auto-invocation language is somewhat broad.

Install this if you want the agent to perform read-only checks across Git history and project state files when repository drift is suspected. Review proposed fixes before approving them, especially in private repositories with sensitive commit history or state logs.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly labels itself as 'deliberately model-invocable' and says it should auto-trigger when 'drift smells,' but that trigger condition is subjective and undefined. Ambiguous auto-invocation criteria can cause the agent to run repository-wide Git inspection without clear user intent, creating unnecessary access to project history and increasing the chance of surprise behavior in sensitive repos.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README says to run the skill "whenever something feels off," which is an imprecise activation condition and does not clearly define when the skill should or should not be invoked. This kind of broad phrasing can overlap with many ordinary situations and may lead to unintended or inconsistent skill use.

Content

No source excerpt is available for this finding.