Back to skill

Security audit

training-delivery-manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward corporate training workflow helper, though users should handle contracts and travel personal data carefully.

Install only if you need a Chinese-oriented corporate training delivery workflow. Before using it with real contracts or travel bookings, confirm output filenames and locations, avoid overwriting existing files, and handle identity numbers, phone numbers, invoices, itineraries, client logos, and photos through approved secure business channels.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says "Use this skill to automate the end-to-end workflow for training projects," but it does not define specific trigger phrases, scope limits, or exclusion conditions. This broad wording could overlap with generic project-management or writing requests and lead to unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The workflow options and output filenames/templates are specified in Chinese, and the skill does not offer the user a language or locale preference. This can violate language-choice policy because it implicitly constrains interaction and generated content to a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill directs the agent to create, modify, save, and deliver a contract document on disk without any explicit user confirmation, safe output location constraints, or handling guidance for sensitive business information. In an agentic environment, file-writing behavior can create unintended documents, overwrite existing files, or process confidential contract data without adequate notice or controls.

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 guide is written as a prescriptive content-creation standard in Chinese and provides no indication that other languages are allowed or that the language requirement is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The guide instructs staff to collect identity number, phone number, and detailed itinerary information, and to send booking details to the lecturer, but it provides no privacy, minimization, access-control, or secure-transmission requirements. In a training-delivery workflow skill, this omission increases the chance of oversharing, insecure handling, or leakage of personally identifiable information and travel data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown template requires Chinese-language output throughout, as shown by the headings, placeholders, and body text. Under the policy, forcing a specific language without offering the user a language or locale choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all instructions in Chinese and does not indicate that users may select another language or that the content is intentionally limited to a Chinese-speaking audience. Under the policy rule for language or locale constraints, forcing a single language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The content appears to require Chinese comprehension throughout, but there is no indication that the skill offers a user language option or that it is intentionally limited to a Chinese-only audience for a documented reason. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file is entirely in Chinese, and there is no natural-language indication that users may choose another language or that the guide is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.