Back to skill

Security audit

subclip-desktop-control

Security checks for vulnerabilities and agentic risk

Overview

The skill received a suspicious verdict because scanners report a risk that recordings could capture sensitive sign-in information, with some analysis incomplete.

Review the skill’s recording instructions before installing. Consider whether you are comfortable with the reported risk that sign-in or verification screens could be captured and saved; the analysis was partial because two local references could not be resolved.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
, not screenshot pixels. Divide screenshot pixels by `scaleFactor`.
- `take_screenshot`: look before you click. Re-take it after any change, because the creator may be using the same screen.
- `pick_screenshot_area`: the creator drags an area; the image comes back. Use when the creator says "this part".
- `open_url`: default `browser` is the agent browser, a separate Chromium profile with its own cookies. Use `browser: "default"` only when the creator asks for their own browser and its sign-ins. To navigate the creator's own Chrome (for example in a recorded window), pass `app: "Google Chrome"`: the page opens as a new tab in the background. Do not type addresses into Chrome's address bar while recording, because its dropdown shows the creator's search history; a background Chrome also ignores plain key presses, so rely on `open_url` with `app`, accessibility clicks and `type_text`.
- `open_app`: open an app by name or bundle id, or a System Settings pane (`general`, `displays`, `priva

Recording-continuity instructions require capturing sensitive authentication screens.

High
Category
Data Exfiltration
Confidence
98% confidence
Finding

The skill explicitly requires keeping recordings running when a sign-in page, security verification, or phone-code prompt blocks progress, including while the creator completes authentication. This conflicts with its later prohibition on recording login pages and can persist sensitive authentication information in saved recordings; forbidding the agent from entering credentials does not prevent their visual capture.

Content

No source excerpt is available for this finding.