ingest-article

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the firecrawl CLI, which it recommends installing via npm (npm i -g firecrawl). Firecrawl is a recognized service for web scraping.
  • [COMMAND_EXECUTION]: The skill executes several shell commands to process the article, including firecrawl, jq, tr, sed, and a local script new_note.sh. Inputs like $URL are quoted to mitigate basic shell injection.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted data from the web.
  • Ingestion points: External article content is fetched from arbitrary URLs via firecrawl scrape in SKILL.md.
  • Boundary markers: Absent. The scraped markdown content is directly interpolated into the final file without delimiters or instructions to the agent to ignore embedded commands.
  • Capability inventory: The skill uses the Bash, Read, and Write tools to create and modify files in the user's Obsidian vault via the new_note.sh script.
  • Sanitization: The article title is slugified for the filename, but the main body content ($MD) is saved exactly as returned by the external scraping service.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:51 PM
Security Audit — agent-trust-hub — ingest-article