Jira BUG Analysis Assistant[Jira-BUG分析助手]

• Outcome: Review
• Latest audit: Jul 7, 2026 · 8:46 AM UTC
• Version: 1.0.1

Overview

The skill appears purpose-aligned for Jira bug reporting, but it handles Jira credentials and raw enterprise issue data with unsafe TLS-bypass guidance and under-disclosed local report persistence.

Review before installing. Use a least-privileged Jira PAT instead of a password, avoid --no-verify/curl -k except in isolated testing, run it only against the intended Jira host, and treat generated HTML/XLS files as sensitive because they can contain raw issue details and identities.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults

Findings (15)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 86% confidence
• Finding: The skill directs the agent to perform network-capable actions against a Jira server but does not declare permissions or otherwise surface that capability in a controlled way. Hidden or undeclared network behavior weakens user awareness and consent, especially when enterprise project data may be queried from internal systems.

Context-Inappropriate Capability

Medium

• Confidence: 76% confidence
• Finding: The skill instructs the agent to install dependencies by running shell commands, which expands the trust boundary from the skill to whatever package versions and indexes are reachable at install time. This creates supply-chain and arbitrary code execution risk if requirements are unpinned, compromised, or unexpectedly modified.

Context-Inappropriate Capability

Medium

• Confidence: 72% confidence
• Finding: The fallback command uses curl plus a Python one-liner and includes credentials directly on the command line, increasing exposure through shell history, process listings, and logging. It also adds another execution path outside the primary script, broadening the attack surface and reducing control over sensitive handling.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill asks for PATs or username/password without a clear warning about sensitivity, storage, or safer alternatives. Collecting raw credentials in conversational flows materially increases the chance of credential disclosure, reuse exposure, and accidental retention in logs or transcripts.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The skill instructs network retrieval of Jira bug data, which may include proprietary project details, without informing the user about privacy and data-transfer implications. Users may unknowingly cause sensitive issue metadata and content to be processed and persisted outside expected governance controls.

Missing User Warnings

High

• Confidence: 94% confidence
• Finding: The skill directs generation of HTML and Excel files in the current working directory containing complete raw issue data, but provides no warning about local persistence or downstream exposure. This creates a straightforward leakage path through shared directories, backups, source repos, endpoint indexing, or accidental attachment/sharing.

Ssd 3

Medium

• Confidence: 95% confidence
• Finding: Embedding the complete raw Jira JSON and full issue list directly into a self-contained HTML report greatly enlarges the disclosure surface. Anyone with access to the file can extract all underlying issue data, including fields that may not be visible in the rendered UI, making accidental exfiltration much easier.

Ssd 3

Medium

• Confidence: 96% confidence
• Finding: The downloadable Excel export includes all raw issue data, including reporter and other detailed fields, creating a direct data-exfiltration mechanism. Spreadsheet files are easily forwarded, indexed, and opened outside controlled systems, which increases the chance of broad internal data leakage.

Credential Access

High

• Category: Privilege Escalation

Content

**必填参数：**
- **Jira Server URL**: 例如 `https://jira.company.com`
- **认证方式**（二选一）：
  - Personal Access Token (PAT)（推荐）
  - 用户名 + 密码
- **Project Key**: Jira 项目标识，例如 `PROJ`

• Confidence: 93% confidence
• Finding: Access Token

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests

• Confidence: 96% confidence
• Finding: requests

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High

• Category: Supply Chain
• Confidence: 90% confidence
• Finding: requests

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

- **结束日期** (`--end-date`): 筛选此日期之前创建的 Bug，格式 YYYY-MM-DD
- **Issue Type 名称** (`--issue-type`): 默认为 `Bug`。如果 Jira 实例使用中文或自定义名称（如 `故障`、`缺陷`），需指定实际名称。如果用户不确定，可先用 REST API 查询项目实际的 Issue Type 列表
- **Severity 自定义字段 ID** (`--severity-field`): 如果 Jira 实例中有「严重程度」自定义字段，提供其字段 ID（如 `customfield_10072`）。告诉用户可以在 Jira 管理后台的自定义字段页面找到此 ID
- 如果用户的 Jira 使用自签名证书，需要添加 `--no-verify` 参数

如果用户没有提供日期范围，建议默认使用最近 90 天。

• Confidence: 91% confidence
• Finding: --no-verify

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

- 401 错误：提示用户检查认证凭据
- 403 错误：提示用户检查项目访问权限
- 连接错误：提示用户检查服务器 URL 和网络/VPN 连接
- SSL 错误：建议使用 `--no-verify` 参数

## Step 4: Analyze the Data

• Confidence: 92% confidence
• Finding: --no-verify

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

parser.add_argument("--end-date", help="Filter bugs created on/before this date (YYYY-MM-DD)")
    parser.add_argument("--max-results", type=int, default=1000, help="Max issues to fetch (default: 1000)")
    parser.add_argument("--page-size", type=int, default=100, help="Results per page (default: 100)")
    parser.add_argument("--no-verify", action="store_true", help="Disable SSL certificate verification")
    parser.add_argument("--severity-field", default="customfield_10072",
                        help="Custom field ID for severity (default: customfield_10072)")
    parser.add_argument("--issue-type", default="Bug",

• Confidence: 96% confidence
• Finding: --no-verify

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

resp = session.post(url, json=payload, timeout=30)
        except requests.exceptions.SSLError as e:
            log(f"ERROR: SSL certificate verification failed: {e}")
            log("Hint: Use --no-verify for self-signed certificates.")
            sys.exit(1)
        except requests.exceptions.ConnectionError as e:
            log(f"ERROR: Cannot connect to {server}: {e}")

• Confidence: 97% confidence
• Finding: --no-verify

VirusTotal

63/63 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.