positron-pull-vscode-server

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches updates from the rstudio/vscode-server repository on GitHub to identify portable changes during the triage phase.
  • [COMMAND_EXECUTION]: Utilizes local bash scripts (enumerate-upstream.sh, check-backlog.sh) and standard npm commands (build-ps, build-check, precommit) to manage the build, verification, and commit process within the local environment.
  • [PROMPT_INJECTION]: The skill processes external data in the form of upstream commit messages and code diffs, which are analyzed by the agent to determine relevance.
  • Ingestion points: Upstream Git commit history and file diffs accessed via git log and git show within the helper scripts.
  • Boundary markers: No explicit delimiters or boundary markers are defined for the parsing and summary of commit data.
  • Capability inventory: The skill is capable of performing Git commits, modifying local project files, and executing project-specific build tools.
  • Sanitization: The workflow relies on manual inspection of code changes by the agent and the user, rather than automated sanitization or filtering of the upstream content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 01:46 PM
Security Audit — agent-trust-hub — positron-pull-vscode-server