gstack-pr-review

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill intentionally collects telemetry and session/repo metadata and includes commands (gstack-telemetry-log, writing ~/.gstack/analytics, and optional codex exec/review) that will transmit repository/diff/session data to external services, representing deliberate data-exfiltration and supply-chain/third-party exposure risks.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). SKILL.md:226-228 and SKILL.md:193-199 require reading PR description/body text via gh pr view --json body ... .body, which is outsider-authored free text (PR author) and is ingested into the agent’s LLM context for scope/intention analysis.