Back to skill

Security audit

Ai Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese ecommerce image-planning helper, with the main caution that it keeps a local plaintext history of generated briefs.

Install only if a Chinese-language ecommerce prompt-planning workflow fits your needs. Avoid entering confidential campaign or product strategy unless you are comfortable with generated brief details being appended to a local plaintext history file.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (14)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest sets the input language to 'zh-CN', and the configuration also defaults to 'zh-CN' without offering a user choice. This is a natural-language locale restriction that is not documented as optional or justified as a region-specific compliance requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The output field requires a '精准中文 Prompt', which mandates Chinese-language output regardless of user preference. This is a language policy concern because the skill does not indicate that users can select another language or consent to the restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The config sets 'default_language' to 'zh-CN', and the surrounding documentation does not mention any user-selectable override. This creates a locale constraint that should either be optional or explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language trigger example is broad enough to overlap with ordinary conversation, which can cause accidental invocation or routing of unrelated user messages into this skill. In multi-skill agent environments, this increases the chance of prompt hijacking, unintended data handling, or execution of the wrong workflow without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The default configuration sets the language to zh-CN, and surrounding docstrings/instructions describe the input and output as Chinese-specific. This is a natural-language locale constraint, but the file does not indicate user opt-in or a documented justification for restricting language/locale.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The analyze flow automatically saves generated brief content derived from user input, creating persistent natural-language records that may include sensitive commercial context. In an agent skill context, such retained prompts are especially risky because they are human-readable, easy to exfiltrate, and may be reused outside the original purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill persists user-derived content to a local history file without any consent, disclosure, retention policy, or sensitivity filtering. Because user prompts may contain product plans, campaign details, or other confidential business information, this creates a privacy and data exposure risk if the filesystem is accessed by other users, processes, backups, or later components.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The history writer appends plaintext prompts, timestamps, product types, and tool choices to a markdown file, which can leak user-provided or inferred business information to anyone with filesystem or backup access. Since the content is stored in readable form and accumulates over time, the impact grows with repeated use and can expose patterns of user activity or confidential marketing plans.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The configuration sets a fixed language value of "zh-CN", which indicates the skill is constrained to Chinese output by default. Under the policy, forcing a specific language without offering user choice or documenting an opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The entire skill history/documentation file is written in Chinese and presents all instructions, headings, and prompt templates only in that language. This can violate a language/locale policy when no user opt-in, alternative language option, or justification for a Chinese-only constraint is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest specifies both input language and default language as "zh-CN", which imposes a fixed locale in the skill configuration. There is no indication of user opt-in, alternative language support, or documented justification that this skill must be Chinese-only.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Lines L073-L080 describe analyze as producing a creative brief dictionary, but at L086-L087 the method may return the result of _ask_clarification when required information is missing. This is an intent/documentation mismatch because the documented behavior presents a single output purpose while the implementation conditionally returns a different response type.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description string "电商规则库 - 策划师专用" states the skill is for planners only and is written solely in Chinese, which can be interpreted as a language/locale restriction without offering any user choice or opt-in. Under the policy rule, natural-language constraints that force a specific language should be documented as optional or justified.

Content

No source excerpt is available for this finding.