skills/openclaw/skills/overleaf/Gen Agent Trust Hub

overleaf

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs the olcli CLI tool from the npm registry and a Homebrew tap during the installation phase.
  • [COMMAND_EXECUTION]: The skill executes olcli commands to interact with Overleaf's API, allowing for project listing, pulling/pushing files, and triggering remote compilations.
  • [PROMPT_INJECTION]: Indirectly ingests external LaTeX source code and project data from the Overleaf platform, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: The olcli pull, olcli download, and olcli sync commands retrieve external project files (SKILL.md).
  • Boundary markers: No explicit delimiters are used to wrap the untrusted content when it is processed by the agent.
  • Capability inventory: The skill has the ability to execute CLI commands, modify the file system, and perform network requests via the olcli tool (SKILL.md).
  • Sanitization: No sanitization or filtering is performed on the content of the LaTeX files pulled from the remote repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:47 PM