ClawHub
Back to skill

Security audit

Overleaf

Security checks across malware telemetry and agentic risk

Overview

This Overleaf skill is transparent about its purpose, but it grants broad browser-session access and can make live Overleaf account changes without enough built-in safeguards.

Install only if you are comfortable letting the tool reuse your logged-in browser session for Overleaf. Prefer a dedicated browser profile or separate Overleaf account, pin and review the pyoverleaf version before granting Keychain access, and require explicit confirmation before any write, delete, sync, download, or invite-acceptance action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger description is broad enough to activate on generic Overleaf/LaTeX-related requests without clearly constraining scope or requiring explicit user intent. In an agent setting, this increases the chance the skill is invoked for sensitive repository access, file sync, or remote project modification when the user did not specifically request those actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly describes accepting Overleaf project invitations programmatically using existing browser-authenticated session cookies, but it does not require a user warning or fresh confirmation before joining a project. That can cause unauthorized workspace access changes, exposure to sensitive documents, and social-engineering-driven enrollment into attacker-controlled projects.

Credential Access

High
Category
Privilege Escalation
Content
## Security Considerations

⚠️ **Keychain Access Required**: pyoverleaf needs "Always Allow" keychain access to read browser cookies. This grants the tool access to your browser's cookie storage.

**Security audit**: We have audited pyoverleaf v0.1.7 and found it safe. The codebase is small and readable. Before installing, agents can self-audit the latest version at the GitHub repo above.
Confidence
97% confidence
Finding
Keychain

Credential Access

High
Category
Privilege Escalation
Content
## Security Considerations

⚠️ **Keychain Access Required**: pyoverleaf needs "Always Allow" keychain access to read browser cookies. This grants the tool access to your browser's cookie storage.

**Security audit**: We have audited pyoverleaf v0.1.7 and found it safe. The codebase is small and readable. Before installing, agents can self-audit the latest version at the GitHub repo above.
Confidence
97% confidence
Finding
keychain

Tool Parameter Abuse

High
Category
Tool Misuse
Content
pyoverleaf mkdir "Project Name/figures"

# Remove file/folder
pyoverleaf rm "Project Name/old-draft.tex"

# Download project as zip
pyoverleaf download-project "Project Name" output.zip
Confidence
84% confidence
Finding
rm "Project Name/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.