Back to skill

Security audit

Project Tracker

Security checks for vulnerabilities and agentic risk

Overview

This project-tracking skill creates and updates local Markdown project records as expected, with no evidence of hidden code, network access, credential use, or destructive behavior.

Install this only if you want the agent to maintain local project-tracking files. To avoid noisy or unintended files, use explicit commands such as asking it to create or update a specific project entry, and review generated project records before relying on them or storing sensitive business details.

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
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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the agent to create and update files in the local workspace but does not prominently require user awareness or consent at the moment of modification. This is dangerous because routine use of the skill can silently alter repository contents, leading to unintended file creation, noisy diffs, or accidental persistence of sensitive project details.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction 'When the user mentions a new project, create projects/.md' is an overly broad trigger that can cause the agent to create files from casual conversation rather than an explicit user request. In a file-writing skill, this creates a real risk of unintended local state changes, clutter, and incorrect project records based on ambiguous mentions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.