The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill documents an attack surface for indirect prompt injection as it is designed to ingest and process external data for semantic search and retrieval.
Ingestion points: The skill description in SKILL.md lists remember, upload, batch, and query commands which ingest text, files, and JSONL data into the memory system.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are documented in the alias file.
Capability inventory: The skill is granted Bash, Read, Write, Grep, and Glob tools in the YAML frontmatter of SKILL.md.
Sanitization: No explicit sanitization or validation logic for external content is described in this alias documentation.

tm