grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized behaviors were detected. The skill's operations are confined to interacting with the user and managing local project documentation.
  • [DATA_EXFILTRATION]: The skill accesses local project files such as kb/vocab.md, CLAUDE.md, and directories under work/. This access is intended for its primary purpose of terminology verification and decision tracking within the project context. No network operations or attempts to exfiltrate data to external domains were identified.
  • [COMMAND_EXECUTION]: The skill uses internal agent instructions to coordinate tasks, such as spawning subagents for focused file lookups. It does not invoke shell commands, subprocesses, or system-level APIs.
  • [PROMPT_INJECTION]: The instructions are focused on guiding the agent's behavior for project alignment. There are no attempts to override safety filters, bypass system constraints, or extract internal system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:02 AM
Security Audit — agent-trust-hub — grill-with-docs