The Agent Skills Directory

[SAFE]: The skill interacts with vendor-controlled infrastructure at api.unifapi.com and mcp.unifapi.com, which is appropriate for its stated functionality.
[SAFE]: Guidance for handling API keys is aligned with security best practices, instructing the agent to utilize environment variables or secure local configuration files rather than soliciting secrets directly within the chat session.
[PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because its primary function is to retrieve and analyze untrusted data from the open web.
Ingestion points: Public data is ingested from external sources (X/Twitter, search engines, news feeds) via the call_api tool through the https://api.unifapi.com endpoint as described in SKILL.md and references/twitter-x.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the retrieved data are present in the skill instructions.
Capability inventory: The skill allows the agent to discover and execute a variety of public-data operations using the Model Context Protocol (MCP).
Sanitization: There is no documentation or instruction within the skill regarding the sanitization or filtering of external content before it is processed by the agent.

unifapi