Back to skill

Security audit

Tap

Security checks for vulnerabilities and agentic risk

Overview

Tap is a coherent browser automation skill, but it can act inside logged-in browser sessions and run third-party scripts, so users should review sources and confirm sensitive actions.

Install only from a source you trust, review the Tap binary or source and Chrome extension before enabling it, and treat browser actions as live actions in your logged-in accounts. Confirm posts, purchases, form submissions, and tab-closing actions before running them, and review community .tap.js scripts before installing or executing them.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:80
Finding

Unpinned Remote Executables and Community Scripts

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly exposes browser actions such as navigation, clicking, typing, API requests, and tab management, but the documentation does not warn that these operations can submit forms, trigger purchases or posts, alter account state, or close user tabs. In an agent setting, missing safety guidance materially increases the chance that an operator or downstream model invokes destructive actions without informed consent.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

bash
git clone https://github.com/LeonTing1010/tap && cd tap
deno compile --allow-read --allow-write --allow-net --allow-env --allow-run --output tap src/cli.ts

2. Install Chrome Extension

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The examples for cross-posting content and installing community skills normalize high-risk actions without cautioning that they may publish external content under the user's account or execute third-party automation scripts. In a browser automation skill, omission of these warnings can directly lead to reputational harm, account misuse, or execution of unreviewed logic.

Content

No source excerpt is available for this finding.