gsd-code-review

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a high-level command dispatcher for code review workflows. It utilizes positional arguments and flags to scope analysis to specific project phases or files, which is standard and expected behavior for CLI-integrated agent skills.
  • [SAFE]: The permitted tools (Read, Bash, Glob, Grep, Write, Agent) are consistent with the stated objective of reading source files, searching for patterns, and spawning specialized sub-agents (gsd-code-reviewer, gsd-code-fixer) to generate reports.
  • [SAFE]: No evidence of credential exposure, data exfiltration, or unauthorized remote code execution was found. All referenced resources, such as the workflow context and gsd-tools, are local to the user's environment and align with the open-gsd vendor namespace.
  • [SAFE]: No obfuscation or prompt injection attempts were detected in the instructions or metadata. The skill follows established patterns for argument parsing and task delegation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-code-review