skills/garrytan/gstack/review/Gen Agent Trust Hub

review

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including pull request bodies, commit messages, and third-party review bot comments (e.g., Greptile, Coderabbit). It mitigates this risk by using the gstack-issue-guard utility to wrap this content in a trust envelope and provides explicit instructions to treat the ingested content as data rather than executable instructions.
  • Ingestion points: SKILL.md (Step 1.5), greptile-triage.md.
  • Boundary markers: Present; the skill uses gstack-issue-guard and explicit 'untrusted DATA' warnings.
  • Capability inventory: Access to Bash, Read, Edit, Write, and sub-agent dispatch via the Agent tool.
  • Sanitization: Present; includes logic to sanitize web queries and uses protective wrappers for PR metadata.
  • [EXTERNAL_DOWNLOADS]: The skill references external CLI tools for extended functionality, specifically aside for web research and OpenAI's codex for adversarial review. These are standard developer tools, and the skill provides instructions for installing the official @openai/codex package.
  • [DATA_EXFILTRATION]: The skill performs telemetry logging and web searches. It includes a specific sanitization routine to strip hostnames, IPs, file paths, SQL, and secrets from queries before they are sent to external services like aside or WebSearch.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool and a localized suite of gstack binary tools (e.g., gstack-skill-start, gstack-gate-diff, gstack-review-log) to automate the code review process. This behavior is consistent with its primary purpose as a developer productivity tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 08:54 AM