ClawHub
Back to skill

Security audit

AANA Release Readiness Check Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a release-readiness checklist skill with no bundled code or persistence; its optional checker guidance is constrained to a redacted review payload.

Before installing, treat this as a checklist for release gating. If you connect it to an external AANA checker, make sure the checker is one you trust and send only the redacted status payload described by the skill.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly claims it is instruction-only and does not call services, but later directs the agent to use a configured AANA checker and transmit a review payload. This creates a deceptive capability mismatch that can cause operators or downstream policy layers to permit network/data egress they believed was impossible, increasing the risk of unintended disclosure or unsafe automation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.