Security audit

Jackyshen Agile Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk agile coaching prompt skill, though its activation wording is broader than necessary.

Install this only if you want an agile coaching prompt helper to activate for Scrum, Product Owner, and related workflow discussions. Be aware it may trigger on generic planning terms like risk or decision-making even when you did not intend to use an agile template.

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

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill's activation criteria are extremely broad and mandatory, covering generic terms like 'risk', 'decision-making', 'pattern recognition', and 'agile' that commonly appear in unrelated conversations. This can cause unintended activation and routing, leading the agent to inject irrelevant guidance, override more appropriate skills, or mishandle user intent across a wide range of normal project discussions.
Content: No source excerpt is available for this finding.