The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted external data sources, creating a surface for potential injection attacks.
Ingestion points: The skill explicitly accepts 'raw notes, polished call summaries, architecture diagrams, diagnostic files, email threads' in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external content as untrusted or to ignore embedded instructions within the ingested notes.
Capability inventory: The skill writes multiple files to the local filesystem (demo/ and opportunity/ directories) and chains execution to other internal skills (warp-listen, warp-scan, thread-qualify).
Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content parsed from external discovery notes.

warp-scout