The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted source materials to generate content, which creates a potential surface for indirect prompt injection attacks.
Ingestion points: The skill explicitly instructs the agent to process external data including published articles, notes, memos, product demos, transcripts, and prior posts (referenced in SKILL.md).
Boundary markers: There are no specific delimiters, boundary markers, or "ignore embedded instructions" directives defined to separate user-provided source material from the skill's own operational instructions.
Capability inventory: The skill references x-api for publishing approved output to X (Twitter), which constitutes a downstream write capability that could be influenced by malicious content within source materials.
Sanitization: No sanitization, filtering, or validation logic is present to inspect source materials for embedded malicious prompts before processing.

content-engine