Back to skill

Security audit

周刊编辑草稿

Security checks for vulnerabilities and agentic risk

Overview

This skill drafts Chinese newsletters from supplied material, with clear limits against collecting contacts or sending messages.

Expect Chinese Markdown drafts requiring editorial review. Before using the installation command, verify the installer and repository source; prefer reviewed, fixed versions. The skill does not need mailing-list access or permission to send messages.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (8)

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

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The description specifies that supplied material becomes a Chinese newsletter draft, without making the output language conditional on the user's preference. Although the title identifies the language, the file provides neither an explicit language opt-in nor a justification requiring Chinese output.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The installation command invokes the unpinned npm package skills through npx, potentially downloading and executing a changing package version with the user's permissions. This is a supply-chain hardening issue rather than evidence of malicious behavior or an MCP server; exploitation would require a compromised or malicious upstream release.

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 23)May include surrounding context.

md
Process a short article, one chapter, or one scenario at a time; tables are limited to 100 rows. Split larger material into batches. The Skill only writes from supplied material and preserves source URLs.

Reference: the use case was checked against [social-media-skills/skills](https://github.com/social-media-skills/skills/blob/main/skills/email-and-newsletter/SKILL.md); this repository's documentation, workflow, and examples are original. 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 25)May include surrounding context.

md
## 来源与许可

业务用途参考 [social-media-skills/skills 的 newsletter 示例](https://github.com/social-media-skills/skills/blob/main/skills/email-and-newsletter/SKILL.md),本仓库的说明、流程和示例均为原创,未复制其内容或代码。仓库以 [MIT-0](LICENSE) 发布。

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The documented installation command executes an unpinned npm CLI through npx and installs skill content from an unpinned repository reference. If an upstream package or repository is compromised, a user following the instructions could execute malicious code or install malicious agent instructions; however, this is a supply-chain reproducibility issue, not evidence of an MCP server or an existing compromise.

Content

No source excerpt is available for this finding.

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.

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 newsletter output without offering a user language choice.

Low
Category
Output Handling
Confidence
90% confidence
Finding

The instruction explicitly requires a Chinese newsletter draft, and the description reinforces that requirement. The skill offers no language opt-in or alternative and provides no regional or compliance justification for restricting output to Chinese.

Content

No source excerpt is available for this finding.