jira-toolkit-free
纯文档Skill,声明exec工具但仅有Markdown指令;验证章节中env扫描凭证行为意图不明,构成文档-行为差异风险。
Why this conclusion was reached
1/4 dimensions flaggedDeclared resources and inferred behavior are broadly aligned.
No obvious high-risk egress or execution signals were found.
The report includes 3 attack-chain steps and 0 severe findings.
Dependency information is incomplete, so supply-chain confidence stays limited.
Attack Chain
Entry · SKILL.md:1
Escalation · SKILL.md:11
Impact · SKILL.md:199
What drove the risk score up
验证配置章节存在 env|grep API|KEY|TOKEN|SECRET 扫描行为,意图不明
声明exec工具可执行任意命令,但文档未明确限定使用场景
声明仅为Jira工具但验证脚本暗示可能收集系统信息
Most important evidence
验证脚本扫描环境变量中的敏感凭证
快速开始章节的验证配置步骤中包含 env | grep -E "API|KEY|TOKEN|SECRET" 命令,该命令遍历环境变量搜索敏感关键字。虽然输出经过脱敏处理,但代码本身暗示可能意图收集系统凭证,文档未解释此操作的合法用途。
SKILL.md:199 exec工具权限声明与实际使用不符
tools字段声明exec工具(shell:WRITE级别),但整个SKILL.md中没有任何实际执行命令的示例,仅通过Markdown指令描述行为。exec工具可被滥用于任意shell执行,但文档未明确限定其使用边界。
SKILL.md:11 依赖第三方CLI工具无版本控制
文档要求安装brew install ankitpokhrel/jira-cli/jira-cli,但未指定版本号,存在供应链风险。攻击者可发布恶意版本覆盖旧版本。
SKILL.md:175 Declared capability vs actual capability
SKILL.md 声明 read, glob, grep 工具 SKILL.md tools字段声明exec工具 无网络工具声明,仅通过jira-cli与Jira API交互 SKILL.md:199 env|grep扫描API|KEY|TOKEN|SECRET Suspicious artifacts and egress
No obvious IOC was extracted.
Dependencies and supply chain
There are no structured dependency warnings.
File composition
SKILL.md