review-overleaf
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script (
overleaf_reviews.py) viabashto interface with the Overleaf API for project listing and comment retrieval. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and summarizing unresolved review threads from an external source (Overleaf). If a project contains maliciously crafted comments, they could attempt to influence the agent's logic when it generates summaries or proposes edits to the local codebase.
Audit Metadata