The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by allowing the agent to ingest untrusted data from external sources.
Ingestion points: Tools such as add_knowledge_base_to_agent (which accepts PDF, DOCX, TXT, HTML, EPUB, and URLs), speech_to_text (processing audio files), and get_conversation (fetching transcripts) allow external data to enter the agent's context.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes this ingested content.
Capability inventory: The skill possesses high-impact capabilities, including making outbound phone calls (make_outbound_call), generating audio (text_to_speech), and writing files to the local file system.
Sanitization: There is no mention of sanitization, escaping, or validation of the external content before it is interpolated into prompts or used by the agent's tools.

elevenlabs-mcp