The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from project files to identify contradictions and staleness.
Ingestion points: Articles in the knowledge/ directory, documents in docs/literature-review/, MEMORY.md, and project session logs.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill utilizes Read, Glob, Grep, Write, and Agent tools to analyze and report on the data.
Sanitization: No evidence of sanitization or filtering of external content before processing is found.
[DATA_EXPOSURE]: The skill references a path at ~/vault/concepts/ to perform promotion readiness checks. This involves reading files outside the immediate project scope from the user's home directory.

knowledge-lint