Back to skill

Security audit

batch-send-mail

Security checks for vulnerabilities and agentic risk

Overview

This bulk-email skill does what it says, but it stores reusable SMTP credentials in plaintext and grants broad email-sending authority that users should review carefully.

Install only if you are comfortable giving the skill access to recipient lists, templates, attachments, and an SMTP account. Use dry-run first, prefer an SMTP-specific app password, avoid passing secrets with --sender-password, and remove or protect config/config.ini because it stores the mail credential in plaintext.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/batch_send_mail.py:64
Finding

SMTP Credentials Stored in a Plaintext Configuration File

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/batch_send_mail.py:313
Finding

SMTP Password Exposed Through a Command-Line Argument

Content
View full analysis
`. 2. The invoking shell, process supervisor, audit subsystem, CI runner, or monitoring agent records or exposes the complete command line. 3. A local user, log reader, CI administrator, or attacker with access to the relevant telemetry retrieves the SMTP credential. 4. The attacker combines the credential with ...[truncated 808 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (15)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The documentation states that SMTP credentials are automatically saved to config/config.ini for later reuse, but it does not prominently warn about the security implications of storing secrets locally. Local plaintext credential storage can expose mailbox access to other users, processes, backups, or source control mistakes, and this is especially sensitive because the skill performs outbound email operations.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill advertises capabilities that read files, write configuration, and access the network, but it does not declare any explicit tool scope or permission boundary. That increases the risk of unintended invocation with broader agent privileges, especially because the skill handles local files and SMTP credentials and can transmit data externally.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition is very broad and explicitly says the skill should be used whenever users say common phrases like '批量发邮件' or similar. In an agent ecosystem, overly broad routing can cause the skill to activate in contexts the user did not intend, leading to accidental access to contact files, attachment paths, or SMTP operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

整个技能说明均以中文撰写,且未声明支持按用户偏好切换语言,也未说明这是仅面向特定中文区域用户的工具。按规则,若技能隐含强制特定语言而无用户选择或正当限定,可构成语言/locale 政策问题。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The evaluation prompt asks the agent to '检查 batch-send-mail 技能' and '验证脚本能正确处理变量替换' without tightly constraining how the skill should be invoked or limiting actions to a safe, non-sending path. In a mail-sending skill, broad verification language can cause the agent to activate the skill in unintended contexts or exercise higher-risk behaviors than necessary, especially if trigger logic is keyed on loose phrases like '批量发邮件' or similar.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This plain-text template is entirely written in Chinese and provides no indication that language selection is optional or user-configurable. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The template content is entirely in Chinese and provides no indication that language selection is optional or limited to a justified region-specific use case. This creates a natural-language policy issue because it imposes a specific locale on all users without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill collects the SMTP password/authorization code and persists it in a local INI file in plaintext without warning the user or applying OS-backed secret storage. If the host, workspace, backups, or repository are accessible to others, the mail account credentials can be recovered and reused for unauthorized email sending or account compromise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file uses Chinese column headers and Chinese product descriptions throughout, which imposes a specific language on downstream use. The file does not indicate that this is a region-specific dataset or provide any opt-in or alternative locale, so it can be considered a natural-language locale policy issue.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The dependency is specified with a lower bound only, so builds can resolve to different versions over time, including newly introduced vulnerable or incompatible releases. In a skill that processes user-supplied CSV/Excel files, dependency drift increases supply-chain risk and makes security review and incident response harder.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
pandas>=2.0.0
openpyxl>=3.1.0

Unverifiable Dependency: pandas has 1 known advisory(ies) (CVE-2020-13091 (** DISPUTED ** pandas through 1.0.3 can unserialize and execute commands from an)), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

openpyxl is also unpinned, which means installations may fetch different versions depending on when and where the skill is deployed. Because this skill reads Excel files from users, lack of strict version control increases exposure to parser-related dependency issues and weakens reproducibility.

Content

Scanner excerpt · requirements.txt (reported line 2)May include surrounding context.

text
pandas>=2.0.0
openpyxl>=3.1.0

Unverifiable Dependency: openpyxl has 2 known advisory(ies) (CVE-2017-5992 (Improper Restriction of XML External Entity Reference in Openpyxl); CVE-2017-5992 (Openpyxl 2.4.1 resolves external entities by default, which allows remote attack)), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Natural-language strings in the top-level docstring and user-facing prompts are exclusively Chinese, with no option to select another language. This can violate language/locale policy when a skill imposes a locale on all users rather than offering choice or documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest describes reading recipient tables, templating, attachments, SMTP configuration, and dry-run preview for bulk email sending. The additional --show-config capability prints live SMTP configuration details, including the sender email and server, which is not necessary to fulfill the stated mailing function and broadens the skill into credential/configuration disclosure behavior.

Content

No source excerpt is available for this finding.