skills/vercel/shop/update-shop/Gen Agent Trust Hub

update-shop

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [External Data Integration]: The skill fetches template rollout logs and versioning information from an official repository on GitHub. This allows the agent to identify necessary updates, which is the primary purpose of the skill.
  • [Command Line Usage]: The shell commands curl and tar are used to retrieve and extract the remote data. These operations are scoped to the update process.
  • [Indirect Prompt Injection Surface]: The skill processes markdown files from an external source to determine how to apply code changes. This ingestion of external data is a potential consideration as it influences the agent's logic.
  • Ingestion points: Fetches rollout logs from the vercel/shop repository.
  • Boundary markers: The instructions do not specify explicit delimiters to isolate the fetched content.
  • Capability inventory: The skill has the ability to read files, write updates to the local project, and perform network requests.
  • Sanitization: There is no mention of specific sanitization or validation of the markdown content before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 02:24 PM
Security Audit — agent-trust-hub — update-shop