Security audit

Build

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed coding workflow helper that can run commands and commit repository changes, but those powers match its stated build-from-plan purpose.

Install this only if you want an agent to make code changes, run local build/test commands, update plan files, and create commits from an existing docs/plan track. Review the plan first and avoid using the skill for general project management despite the broad description text.

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 (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The summary/description presents very broad use cases such as project management, planning, tracking, collaboration, and automation workflows, which can cause the skill to be invoked outside its intended narrow purpose of executing an existing implementation plan. Over-broad triggers increase the chance that an agent will select this skill in the wrong context and run read/exec actions on a repository when a safer or more specific skill should have been used.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The deployment/usage guidance is generic ('call this skill with necessary input parameters') and does not constrain when the skill should run or what preconditions must be satisfied. In an agentic environment with exec capability, vague activation guidance can lead to unintended execution, including repository modification or command execution in contexts where no validated plan exists.

Static analysis

No suspicious patterns detected.