Security audit

Seismograph

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local code-change impact checklist with one broad trigger phrase, but no hidden execution, network use, persistence, or credential handling.

Install this if you want a conservative checklist for understanding code-change impact. Be aware it may activate on casual wording about a change being simple; users should keep invocation tied to concrete proposed changes, public interfaces, schemas, APIs, or PR review.

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: 94% confidence
Finding: The invocation rule 'When someone says "this should be a simple change"' is overly broad and keyed to common conversational phrasing rather than a clear technical condition. In an agent environment, this can cause the skill to trigger unexpectedly on routine discussion, creating prompt-scope creep and potentially steering the agent into unnecessary analysis or away from the user's actual task.

Static analysis

No suspicious patterns detected.