write-docs

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/save_clipboard.py to capture images from the user's clipboard and save them to a specified local directory path. This is used for generating documentation visual aids.
  • [DATA_EXPOSURE]: The skill is designed to read source code from a sibling directory ../browseros-server to understand feature implementation. While this accesses files outside the skill's own directory, it is within the expected scope of a documentation tool for the project ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading the external ../browseros-server codebase to generate documentation. While this creates a theoretical surface for indirect injection via malicious code comments, the resulting output (MDX documentation) and the specific capability set present minimal risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 10:40 AM