Security audit

Chief Information Security Officer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only CISO guidance skill whose security operations advice is broad but coherent with its stated purpose and not backed by hidden code or persistence.

Install only if you want broad security-program and incident-response guidance. Do not paste live secrets into chat, and require explicit human approval before any real-world destructive or high-impact action such as disabling accounts, rotating production credentials, taking systems offline, wiping hosts, notifying customers, or accepting third-party risk.

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

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Credential Access

High

Category: Privilege Escalation
Content: ## Vendor Termination Checklist - [ ] Data return/deletion confirmed in writing - [ ] Access credentials revoked - [ ] SSO/OAuth integrations removed - [ ] DNS/network connections removed - [ ] API keys rotated
Confidence: 70% confidence
Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The 'When to Use' section says the skill applies when a user needs 'CISO-level guidance for information security' and describes the agent as handling broad security operations, compliance, risk management, and incident response. This is an expansive, ambiguous activation scope without explicit trigger phrases, exclusions, or negative examples, which could cause unintended invocation for many generic security-related requests.

Vague Triggers

Low

Confidence: 82% confidence
Finding: This markdown file provides broad incident response procedures but does not define specific trigger phrases, invocation boundaries, or exclusion conditions. In a skill context, such generic security content could be matched too broadly unless the activation scope is constrained elsewhere.

Static analysis

No suspicious patterns detected.