migration

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external data from sitemaps and online research, creating a potential surface for indirect prompt injection attacks.
  • Ingestion points: sitemap.xml files used for route discovery and external synthesis provided by the agent:research skill.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when processing sitemap URLs or research data.
  • Capability inventory: The skill uses shell commands (git, pnpm), browser automation via Playwright, and file modification capabilities.
  • Sanitization: Absent; there is no mention of sanitizing or validating the content of the sitemap or the research results before use.
  • [COMMAND_EXECUTION]: The skill uses standard development tools including git and pnpm. These are used for version control (stash/pop) and dependency management (pnpm install), which are necessary and expected for a migration-focused skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 02:54 PM
Security Audit — agent-trust-hub — migration