code-reviewer
Analysis
This is mostly an instruction-only code review skill, but it also includes overbroad team-metrics instructions that reference specific local repositories, named contributors, and credentialed PR APIs.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
评估团队代码仓库本地地址 C:\yanfayun\gpc-srv C:\yanfayun\gpc-provider-orchestrator ... **数据范围:** 本周内的所有代码提交与评审活动
The rule directs the agent toward multiple hardcoded local repositories and all weekly commit/review activity, which is broader than normal user-selected code review and lacks clear scoping or approval controls.
Agent MUST execute this command to generate coverage data:
go test "./..." \
-v \
-coverprofile="coverage.out" \
-covermode=count \
-gcflags=-l \
-json > test-report.jsonRunning Go tests is purpose-aligned for coverage analysis, but it executes project test code and writes coverage/report files.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
认证方式: Bearer Token ... 使用说明 - 需要有效的访问令牌(Access Token)
The rule introduces authenticated PR-statistics API access using a Bearer token, while the registry declares no required credentials or environment variables.
