The Agent Skills Directory

[SAFE]: The skill instructions are focused on architectural review (grilling) and the maintenance of local documentation files like CONTEXT.md and ADRs. It does not perform any dangerous operations.
[SAFE]: No external network requests, remote code execution, or credential exposure patterns were identified in the skill files.
[SAFE]: No obfuscation techniques or malicious prompt injection patterns were found.
[INDIRECT_PROMPT_INJECTION]: The skill reads from and writes to repository files, creating a potential surface for indirect prompt injection if the processed repository contains malicious content.
Ingestion points: Reads from project files including CONTEXT.md, CONTEXT-MAP.md, docs/adr/, and source code under src/.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the documentation files it processes.
Capability inventory: The agent is authorized to read local repository files and create or update documentation files (ADRs and glossaries).
Sanitization: No explicit content sanitization or validation logic is specified for the data being read from the project files.

grill-me