The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources, creating a vulnerability surface for indirect prompt injection.
Ingestion points: Data is gathered from SerpAPI (Google Hotels), TripAdvisor ratings/reviews, Airbnb listings (via MCP), and web searches for Trivago and LiteAPI.
Boundary markers: The workflow instructions do not define clear boundaries or delimiters to isolate untrusted external content from the agent's core instructions.
Capability inventory: The skill performs complex orchestration including benefit-adjusted price calculations, property tagging, and generating final recommendations based on the aggregated data.
Sanitization: No explicit sanitization or instruction-filtering mechanisms are mentioned for handling potentially malicious content embedded in hotel descriptions or user reviews.
[EXTERNAL_DOWNLOADS]: The skill requires the use of external execution environments and tools.
It references 'npx MCP' for Airbnb searches, which involves the dynamic execution of Node-based tools.
It specifies a requirement for Docker-based headed browsers (via Patchright/Xvfb) to interact with travel portals and VRBO, introducing dependencies on external containerized environments.

compare-hotels