Security audit

Ops

Security checks for vulnerabilities and agentic risk

Overview

This is a broad operations guidance skill with no executable code, hidden behavior, persistence, or external data flow in the inspected artifact.

Install this if you want general operations playbooks and process guidance. Use care when applying it to incidents, vendor contracts, or internal documentation because the useful inputs may be sensitive business information, but the skill itself does not include code or hidden data handling.

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

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

Findings (1)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill description is extremely broad and covers engineering, business, organizational workflows, incidents, deployments, vendors, documentation, and team processes. That makes activation boundaries unclear, increasing the chance the agent invokes this skill for many unrelated requests and applies operational authority or process guidance in contexts where a narrower, more constrained skill should be used.

Static analysis

No suspicious patterns detected.