Security audit

Tech Debt Ledger

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only planning skill for estimating technical debt, with no hidden code execution, installs, persistence, or external data transfer.

Installers should understand that the skill is meant to help structure technical-debt discussions and audits. It may prompt analysis of project files when used for debt discovery, but the artifact does not include code, network access, dependency installation, credential handling, or persistence.

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: 85% confidence
Finding: The 'When to Invoke' section lists general situations such as 'Sprint planning,' 'Quarterly reviews,' and 'When velocity is declining' without defining specific trigger phrases, boundaries, or exclusion conditions. In a markdown skill description, this can create overly broad activation criteria and increase the chance of unintended invocation during ordinary team conversations.

Static analysis

No suspicious patterns detected.