ClawHub
Back to skill

Security audit

Ai Readiness Checklist

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only AI readiness questionnaire, with a minor caution that one report template adds Resomnium branding and a consulting contact link.

Reasonable to install for a lightweight readiness assessment. Be aware that generated reports may include Resomnium branding and a consulting contact link if the template is used, and avoid entering confidential organizational details unless you are comfortable sharing them in the chat context.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
templates/assessment-report-template.md:105
Finding

Hardcoded Third-Party Branding and Promotional Link in Generated Reports

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 177)May include surrounding context.

md
**"Pilot Trap"**: High scores on Q6 (AI talent) and Q9 (deployment) are both low (c or d). Organization can build prototypes but can't ship. Fix: Dedicated ML engineering team + MLOps investment.

**"Governance Debt"**: Q4 (exec sponsorship) is high (a or b) but Q10-12 (governance) are all low. The org is moving fast without guardrails. Fix: Formalize policy before next deployment.

**"Data Mirage"**: Q1 (accessibility) is high but Q2 (quality) is low. Teams think they have usable data until they actually try to train on it. Fix: Data quality audit before any model work.

Static analysis

No suspicious patterns detected.