Back to skill

Security audit

店铺FAQ知识库

Security checks for vulnerabilities and agentic risk

Overview

The skill creates Chinese FAQs from supplied store policies, with no customer messaging, account access, or background activity.

Use this skill for Chinese FAQs, supply approved customer-facing policies, and review the draft before publishing. Its bundled examples are fictional and do not establish your store's policies.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

The skill specifies Chinese FAQ output without offering a language choice or opt-in.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The instruction to turn policies into a “reusable Chinese FAQ” explicitly fixes the output language. The file provides no user language choice, opt-in, or documented regional justification for this constraint.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.en.md (reported line 39)May include surrounding context.

md
## Attribution and license

The original Chinese content and fixtures here were independently written. The public [marketingskills sales-enablement Skill](https://github.com/coreyhaines31/marketingskills/blob/main/skills/sales-enablement/SKILL.md) was consulted only for its general use case; no source code or copy was reused. Licensed under [MIT-0](LICENSE).

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 43)May include surrounding context.

md
## 来源与许可

本仓库为原创中文说明与示例,仅参考 [marketingskills 的 sales-enablement Skill](https://github.com/coreyhaines31/marketingskills/blob/main/skills/sales-enablement/SKILL.md) 的公开用途定位;未复制其源码或文案。图标与推广视觉为本仓库原创生成素材。代码与文档采用 [MIT-0](LICENSE) 许可。

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

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.

The skill specifies Chinese FAQ output without offering a language choice or requiring user opt-in.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The description explicitly requires producing Chinese FAQs (中文FAQ), rather than merely using Chinese to describe the skill. No user language choice or regional justification is provided, and implicit invocation is enabled on line L8.

Content

No source excerpt is available for this finding.

The manifest requires Chinese-language FAQ output without consistently obtaining user opt-in.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The description and short description specify Chinese FAQ output, while several invocation triggers request only FAQ organization or missing-field identification. Because implicit invocation is enabled, the skill can impose Chinese output without an explicit language request; the manifest provides no regional or compliance justification for that restriction.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

The skill requires Chinese-language FAQ output without offering a language choice or explaining why that language is necessary.

Low
Category
Output Handling
Confidence
96% confidence
Finding

Line 8 explicitly specifies a Chinese FAQ, reinforcing the Chinese-output requirement in the description on line 3. The skill provides neither user opt-in nor a documented regional or operational justification for fixing the output language.

Content

No source excerpt is available for this finding.