The Agent Skills Directory

[Data Exposure & Exfiltration] (MEDIUM): The skill mandates routing traffic through third-party proxies (e.g., apn-latest.onrender.com, corsproxy.io, wsrv.nl) to bypass regional restrictions. This exposes request metadata and potentially sensitive query information to the operators of these non-whitelisted external services.
[Prompt Injection] (MEDIUM): The skill is designed to ingest and process data from external providers (TMDB, Kinopoisk) and multiple proxies, creating a surface for indirect prompt injection. 1. Ingestion points: Data retrieved from TMDB and Kinopoisk metadata fields. 2. Boundary markers: None described in the skill instructions to delimit untrusted content. 3. Capability inventory: Network communication to multiple external endpoints via tmdbClient.js. 4. Sanitization: No logic is provided for sanitizing or validating external metadata before it is presented to the agent.
[External Downloads] (LOW): The skill references multiple external domains for data retrieval but does not show patterns of downloading and executing remote scripts or binaries.

resilience-core