Back to skill

Security audit

伏笔回收清单

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently analyzes supplied story excerpts, with no material security concern found beyond routine installation precautions.

Use a reviewed installer version and fixed skill revision when possible. Supply only story material you intend your agent to process; the analysis workflow does not require running the promotional renderer.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (9)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied script is a standalone promotional graphic renderer. It accepts no chapter or scene text and implements no foreshadowing extraction, status tracking, payoff recommendations, missing-information reporting, or 100-line limit. Although its promotional wording references the declared skill, that thematic connection does not make image generation an implementation of the described analysis.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

就所提供的代码而言,其直接行为是安装技能,主要功能与声明的文本分析用途不同。虽然该命令可能只是相关技能的安装说明,但未提供被安装技能的实现,因此无法验证其是否具备声明中的分析功能、100行限制或材料不足处理机制。此结论仅针对所给代码,不推断远程技能的具体行为或恶意性。

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes the unpinned skills npm package through npx, potentially executing a future compromised release with the installing user's privileges. The referenced skill source is also not tied to an immutable revision. This is an installation supply-chain risk rather than an MCP-server configuration issue; its placement in a user-invoked README command reduces exposure compared with automatic execution.

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 26)May include surrounding context.

md
## Reference and license

The public [story-skills repository](https://github.com/danjdewhurst/story-skills) and its [revision-continuity Skill](https://github.com/danjdewhurst/story-skills/blob/main/skills/revision-continuity/SKILL.md) were consulted only for business-purpose context. This repository contains original instructions and examples, with no copied text or code, and is released under the [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 26)May include surrounding context.

md
## 参考与许可证

业务用途参考:[story-skills](https://github.com/danjdewhurst/story-skills) 的公开仓库及其 [revision-continuity Skill](https://github.com/danjdewhurst/story-skills/blob/main/skills/revision-continuity/SKILL.md)。本仓库的说明、流程和示例均为原创,未复制其文本或代码;本仓库以 [MIT-0](LICENSE) 发布。

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

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes an unpinned npm package through npx, allowing the code executed during installation to change without any change to this README. A compromised future release could execute with the installer's permissions; however, this is a user-invoked installation example, not an automatic execution instruction or an MCP server configuration as the static finding suggests.

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 script implements promotional-image generation, which is outside the declared foreshadow-tracking purpose.

Low
Category
Excessive Agency
Confidence
93% confidence
Finding

Lines L25–L45 load an illustration, compose a branded promotional layout, and write assets/promo-1600x900.png. This is a marketing-asset capability rather than an implementation detail of analyzing supplied narrative text or producing a foreshadow-recovery table, and the manifest does not declare it.

Content

No source excerpt is available for this finding.