travel-requirements-expert

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary functionality is implemented through clear, non-obfuscated markdown instructions and a Python script that uses standard libraries to manage local folders and files.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from web searches (Exa) and web scraping (Firecrawl), which creates a surface for indirect prompt injection if external sources contain malicious instructions.
  • Ingestion points: Research findings gathered from Exa search and Firecrawl scraping tools are written to 03-context-findings.md and processed by the agent in later phases.
  • Boundary markers: The instructions do not explicitly require the agent to wrap external findings in delimiters or ignore instructions found within research data.
  • Capability inventory: The skill has the ability to write files to the local file system (via scripts/create_requirements_folder.py) and perform additional network searches via MCP tools.
  • Sanitization: There is no explicit requirement for the agent to sanitize or filter the content retrieved from external research before using it to generate the final specification.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:34 PM