Security audit

Workflow Execution

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow guide for planning, tracking, delegating, and verifying non-trivial work, with no hidden code or exfiltration behavior found.

Before installing, be aware that this skill encourages creating or updating project trackers, GitHub issues/comments, local plan files, branches, PRs, and spawned agent sessions for non-trivial work. Use the local-file fallback or narrow the workflow manually when public tracker updates or agent handoffs would be unnecessary.

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 instruction 'Run this workflow for any meaningful work' is highly subjective and lacks clear boundaries for when the skill should or should not be used. Although later sections add some triggers, this top-level activation phrase is broad enough to overlap with routine work and may lead to unintended invocation.

Static analysis

No suspicious patterns detected.