The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script ../obsidian-notes-karpathy/scripts/scan_query_scope.py to establish the retrieval boundaries for vault queries.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes content from various ingestion points in an external knowledge base.\n
Ingestion points: wiki/index.md, wiki/live/indices/INDEX.md, wiki/live/indices/CONCEPTS.md, wiki/live/indices/SOURCES.md, wiki/live/indices/QUESTIONS.md, wiki/briefings/{role}.md, and archived query results in outputs/qa/.\n
Boundary markers: Absent. The skill provides logical retrieval constraints but lacks technical delimiters or instructions to ignore embedded commands within the ingested data.\n
Capability inventory: The skill can read local files, write to the outputs/qa/ directory, and execute a local Python script.\n
Sanitization: Absent. The skill does not implement validation or sanitization of the content retrieved from the Obsidian vault.

kb-query