weekly-lab-sync

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh CLI to interact with the GitHub API for repository discovery, commit tracking, and reading file contents. It also uses curl to download plots and images from GitHub into the user's local vault attachments folder.
  • [EXTERNAL_DOWNLOADS]: Fetches research notebooks and image files from remote GitHub repositories to incorporate them into the local Obsidian vault environment.
  • [PROMPT_INJECTION]: The skill processes untrusted content from external GitHub repositories (lab_notebook.md), presenting a surface for indirect prompt injection.
  • Ingestion points: Reads markdown file contents from various analysis folders in research compendia.
  • Boundary markers: The skill does not implement explicit delimiters or boundary markers when interpolating external content into the agent's context for summarization.
  • Capability inventory: The agent has access to gh and curl for network/read operations and possesses file-write capabilities within the local Obsidian vault.
  • Sanitization: There is no evidence of sanitization or validation of the fetched markdown content before it is processed or appended, although the skill requires explicit user approval before any modifications are applied.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 07:33 PM