The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the grep command to identify relevant keywords within the local wiki/ directory. This is a standard functional component of the workflow.\n- [PROMPT_INJECTION]: The skill reads and processes data from local Markdown files, creating a potential surface for indirect prompt injection.\n
Ingestion points: Reads text from index.md, wikilinked pages, and results from grep searches.\n
Boundary markers: No delimiters or explicit instructions are provided to the agent to treat ingested file content as data rather than instructions.\n
Capability inventory: The skill can read local files and write or append information to wiki/analyses/ and log.md.\n
Sanitization: No validation or sanitization is performed on the text read from the local files.

brain-query