The Agent Skills Directory

[SAFE]: No malicious patterns, data exfiltration, or unauthorized code execution were detected. The skill's logic is dedicated to maintaining documentation and domain models.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from the repository's files.
Ingestion points: Reads repository files including CONTEXT.md, CONTEXT-MAP.md, ADR files, and source code files.
Boundary markers: Absent. The skill does not use explicit delimiters to isolate data read from files from its own operating instructions.
Capability inventory: Includes file system reading and the creation or modification of specific documentation files (CONTEXT.md and ADRs).
Sanitization: Absent. Content from ingested files is processed without validation or filtering.
[COMMAND_EXECUTION]: The skill performs expected file system operations to explore the codebase and update project documentation, which is consistent with its intended functionality.

grill-with-docs