ClawHub
Back to skill

Security audit

reconcile

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only reconciliation checklist for Git/worktree drift and does not show hidden execution, persistence, credential use, or automatic file mutation.

Install only if you want a model-invocable repository drift check that may read recent Git history, branch diffs, and project state files. Review proposed fixes before approving any edits, especially in repositories with sensitive planning or decision-log files.

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
93% confidence
Finding

This markdown file defines activation behavior, so SQP-1 applies. Phrases such as "auto-triggering when drift smells" and "when something feels off" are subjective and lack clear boundaries, increasing the chance of unintended invocation during ordinary troubleshooting or review workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The phrase "whenever something feels off" is ambiguous and subjective, making it unclear when the skill should be invoked versus not invoked. This can cause unintended or inconsistent activation because it overlaps with many routine situations rather than a narrowly defined reconciliation scenario.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.