p-md-to-slides

Pass

Audited by Gen Agent Trust Hub on May 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the gws CLI to interact with the Google Slides API (creating presentations, batch updates, and retrieving thumbnails). It also uses python3 heredocs to parse the input Markdown file and generate the JSON payloads required for the API requests.
  • [EXTERNAL_DOWNLOADS]: In Step 7, the skill uses curl to download slide thumbnails to a temporary local directory (/tmp/p-md-to-slides/). These URLs are retrieved directly from the Google Slides API for the purpose of verifying the visual output of the deck. This is a standard functional requirement for an agent to 'see' its work.
  • [SAFE]: The skill logic is provided as transparent shell commands and Python snippets within the markdown instructions. It does not attempt to access sensitive system files (e.g., .ssh, .env) or execute code from untrusted remote sources. All operations are scoped to the user's provided Markdown input and the Google Slides API.
Audit Metadata
Risk Level
SAFE
Analyzed
May 30, 2026, 01:40 AM
Security Audit — agent-trust-hub — p-md-to-slides