skills/aloth/overleaf-skill/overleaf/Gen Agent Trust Hub

overleaf

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the olcli utility from the author's verified repositories using Homebrew or npm. These resources are owned by the vendor and are necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: Provides an interface for executing LaTeX management commands such as pull, push, sync, and compile. These operations are limited to the user's project directories and the Overleaf platform.
  • [CREDENTIALS_UNSAFE]: Includes instructions for authenticating with an Overleaf session cookie. The skill documentation describes standard local storage locations for these credentials, such as environment variables and configuration files in the user's home directory.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes LaTeX data pulled from external sources.
  • Ingestion points: The olcli pull command downloads external LaTeX project content into the local environment as described in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are defined for processing downloaded content.
  • Capability inventory: The skill can execute file operations and network syncs via olcli sync, push, and upload as seen in SKILL.md and README.md.
  • Sanitization: Content is downloaded and processed as-is without specific validation or filtering steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 01:52 PM
Security Audit — agent-trust-hub — overleaf