Back to skill

Security audit

报告写作

Security checks for vulnerabilities and agentic risk

Overview

The skill is not plainly malicious, but it asks for command execution and broad file/tool authority that are not well scoped for a daily-report writer.

Install only if you are comfortable granting this skill file read/write access and potential command execution. Prefer running it in a sandbox or with exec disabled, and manually confirm any file writes are limited to the intended reports directory.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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 (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:25
Finding

Unnecessary Command-Execution Capability Violates Least Privilege

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill claims it generates daily reports and writes them into a reports directory, but the provided file contains only descriptive metadata and no implementation. This mismatch can mislead users and downstream agents into assuming filesystem-modifying behavior exists or is safe, creating trust and operational integrity risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation says the skill writes Markdown files to the reports directory but does not provide a clear user-facing warning that it may modify the filesystem. In a skill that includes write and exec tools, silent or under-disclosed file modification raises the risk of unintended changes, overwrites, or misuse by automated routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill uses very broad invocation language covering general writing, marketing copy, title optimization, content creation, and workflow assistance. Overbroad descriptions can cause inappropriate auto-selection by agents, increasing the chance that a skill with read/write/exec permissions is invoked in contexts beyond its intended scope.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The FAQ states the skill automatically fetches and organizes related information, but no collection or processing logic is present. This is dangerous because it overstates capability and may cause users to trust unverified or nonexistent data handling, including assumptions about what sources are accessed and how content is processed.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The security section claims commands are restricted to a whitelist and that network communication is protected with HTTPS certificate validation, but no code enforces either control. False security assurances are especially risky here because the skill declares exec capability, which can lead users or agents to rely on protections that do not actually exist.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description says the skill supports Chinese interaction, and the document is predominantly Chinese, but it does not clearly offer users a language choice or explain that the skill is intentionally region- or language-specific. This may violate language/locale neutrality expectations for broadly advertised skills.

Content

No source excerpt is available for this finding.