ClawHub
Back to skill

Security audit

document-ahead-coding

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed documentation-first workflow that writes planning notes into the project and does not contain hidden code, network access, credential use, or persistence beyond normal repo documents.

Install this if you want agents to create and maintain planning docs before coding. Be aware it may add persistent records of discussions, decisions, and rejected ideas under docs/, so avoid putting secrets or sensitive private details into those planning notes.

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 manifest says to use the skill for 'any non-trivial change' and lists broad cases like 'new feature, refactor, bug fix, or migration' without clear boundaries or exclusion conditions. In a markdown/manifest context, this is an ambiguous trigger scope that could cause the skill to activate for a very wide range of normal coding conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Phrases like 'More than a trivial one-file edit' and 'any work needing more than one step' are subjective and overlap with many everyday coding tasks. Because the skill does not provide negative examples or sharper constraints here, the trigger remains vague for a markdown skill description.

Content

No source excerpt is available for this finding.