use-fullstackrecipes

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch setup guides, recipes, and cookbooks in Markdown format from fullstackrecipes.com using curl commands.
  • [COMMAND_EXECUTION]: Instructions provide examples for using curl to fetch remote content and bunx skills add to install and execute package-based tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to fetch and follow external Markdown recipes exactly as written.
  • Ingestion points: External Markdown files fetched from fullstackrecipes.com/recipes/*.md and the index at fullstackrecipes.com/llms.txt.
  • Boundary markers: No specific boundary markers or delimiters are provided to isolate the fetched external content from the agent's core instructions.
  • Capability inventory: The skill leverages curl for network access and bunx for package execution, which could be used to perform actions defined in the fetched content.
  • Sanitization: There is no evidence of sanitization, filtering, or validation performed on the external Markdown content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:02 PM
Security Audit — agent-trust-hub — use-fullstackrecipes