ClawHub
Back to skill

Security audit

AI README Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed documentation generator that reads project code and writes agent-facing README/Cursor rule files without hidden execution or exfiltration behavior.

Install or use this when you actually want AGENTS.md and .cursor/rules/ai-readme files created or refreshed. Review the generated agent-facing files afterward because they can influence future coding sessions, and make sure project-specific secrets or private local details were not summarized into the docs.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
## Safety rules

- Do not invent APIs, commands, paths, services, or business rules. If uncertain, write `<!-- TODO: verify ... -->`.
- Do not overwrite existing files under `.cursor/rules/ai-readme/manual/`.
- If `AGENTS.md` already exists, read it first. Preserve useful human-written constraints and update only project facts that can be verified from code.
- Generated files under `.cursor/rules/ai-readme/generated/` may be refreshed from code evidence.

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.

md
## Generated information

- Generated at: <!-- YYYY-MM-DD HH:mm -->
- Project root: <!-- path or repository name -->
- Evidence scope: <!-- key files/directories scanned -->

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broad enough that it could be invoked for many loosely related requests about documentation, project rules, or AI-friendly setup. Over-broad activation increases the chance the agent scans and rewrites project files when the user intended a narrower action, creating unnecessary exposure to repository contents and unintended file modifications.

Content

No source excerpt is available for this finding.