ClawHub
Back to skill

Security audit

Technical Documentation Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-template skill with no executable payload or hidden behavior, though users should review any generated operational commands before running them.

Install only if you want an agent to help audit and generate technical documentation. Treat generated runbooks, migrations, and pipeline setup steps as drafts: review scope, environment, backups, and approvals before executing any commands against real systems.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The README instructs users to invoke the skill with the generic phrase "Audit the docs for my project," which is a common request that could overlap with ordinary conversation. The file does not define specific trigger boundaries, exclusions, or negative examples to clarify when this skill should activate versus when a general assistant should respond normally.

External Transmission

Medium
Category
Data Exfiltration
Content
### Example

\`\`\`bash
curl -X POST https://api.example.com/v1/users \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Example

\`\`\`bash
curl -X POST https://api.example.com/v1/users \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill exposes very broad trigger phrases such as "Review this doc", "Write a README", and "Set up docs pipeline" that overlap with ordinary user requests. In agent environments, ambiguous activation can cause this skill to run unexpectedly and steer the conversation toward generating operational guidance or documentation artifacts the user did not explicitly request.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The runbook section instructs the model to produce mitigation, fix, verification, and rollback commands without embedding safety guardrails. If used on real infrastructure, the generated steps could include disruptive or destructive actions that an operator might execute directly, especially because the template emphasizes copy-paste commands and rapid incident response.

Static analysis

No suspicious patterns detected.