grill-with-docs

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is intended for documentation management and domain modeling analysis. No malicious patterns, obfuscation, or safety bypass instructions were detected.
  • [COMMAND_EXECUTION]: The skill involves reading and writing documentation files within the local repository. These file system operations are limited to documentation-specific files (ADRs and CONTEXT.md) and do not include arbitrary shell command execution.
  • [DATA_EXFILTRATION]: While the skill explores the codebase to verify domain terminology, it lacks any network-enabled capabilities to send data to external servers. No hardcoded credentials or access to sensitive configuration files (like SSH keys or .env files) were observed.
  • [PROMPT_INJECTION]: The skill reads data from the local repository, which is a potential surface for indirect prompt injection. However, since the skill's capabilities are restricted to local documentation updates and it lacks network or system-level execution tools, the risk is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 11:08 AM
Security Audit — agent-trust-hub — grill-with-docs