Back to skill

Security audit

News Sum

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent news-summary tool, but its email step uses an unsafe shell command with user and web-generated content.

Review before installing. Use it only if you are comfortable with web searches, local archive writes, a rolling brief file, and email through a configured Gmail tool. The email command should be fixed to avoid shell interpolation and should require explicit confirmation before sending any generated report or attachment.

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

Error
Location
SKILL.md:95
Finding

Shell Command Injection in Email Delivery

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
references/journalist.md:7
Finding

Indirect Prompt Injection Exposure Through Untrusted News Content

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description is broad enough that the skill may activate on loosely related user requests, increasing the chance of unintended execution of search, file generation, or email-delivery behavior. Because this skill can also transmit content externally, ambiguous activation boundaries materially raise the risk of actions the user did not clearly intend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The email-delivery flow sends generated content to an external recipient without requiring an explicit warning or confirmation that data is leaving the system. In context, this is more dangerous because the skill handles generated summaries and attachments, so accidental activation or recipient mistakes could cause unintended disclosure outside the workspace.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

技能目标本身是生成新闻摘要并发送到邮箱;发送邮件是合理目的,但这里的实现明确依赖 shell 命令调用而不是更受限的邮件接口。对一个新闻汇总技能来说,暴露可执行外部命令的能力并非其目的直接要求,属于与场景不相称的能力。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill is written as a Chinese-only operating prompt and specifies the output structure in Chinese, but it does not indicate that language selection is optional or region-specific. This can violate language/locale policy when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Lines L45-L47 explicitly instruct the skill to use web_search to search for and retrieve additional news, which implies network access to external sources. The markdown provides no warning about external requests or the privacy implications of transmitting search queries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The template and headings are written in Chinese and present the final file format as the required output format, with no indication that users may choose another language. This is a natural-language locale policy issue because the skill appears to mandate a specific language without opt-in or a documented region-specific need.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions explicitly require 中文摘要+分析 for all summaries, which imposes a fixed output language. Because the file does not offer user opt-in or explain a justified region-specific constraint, this is a natural-language locale policy violation under the stated rules.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Line L03 states that the editor should generate a draft.md file, and L81 provides a concrete output path, but the markdown does not warn the user that the skill will create or overwrite a file in the workspace. For markdown files, omission of warnings about behavior that affects user data or workspace contents is in scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file instructs the agent to create or overwrite a JSON file under workspace/archive/news/json/, which is a file-write operation affecting user or workspace data. The description provides the target path and naming scheme but does not include any warning or disclosure that the skill will write files to the local workspace.

Content

No source excerpt is available for this finding.