grill-with-docs
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to facilitate 'grilling' sessions where the agent interviews the user to refine project terminology and documentation. It follows a structured process for updating
CONTEXT.mdand ADR files based on clear templates provided in the skill package. - [DATA_EXPOSURE]: The instructions direct the agent to explore the codebase for existing documentation and source code to cross-reference user claims. This is consistent with its stated purpose of documentation management. No sensitive file paths (e.g.,
.env,.ssh) are targeted, and no network operations for data transmission are present. - [COMMAND_EXECUTION]: The skill does not contain any shell commands, scripts, or instructions that would lead to unauthorized command execution. It relies on standard file-system interactions for reading and writing documentation.
- [PROMPT_INJECTION]: The instructions are clear and focused on the domain-modeling persona. There are no attempts to bypass safety filters or override system constraints.
Audit Metadata