Back to skill

Security audit

叙事视角诊断与修订

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: it found no issues in one completed scan, while another scan reported an unpinned install command and possible mismatch between the declared editing purpose and installation behavior.

The verdict is benign, but the evidence is incomplete: Skillspector was partial, with one script only partly inspected and binary images outside its analysis, and its tool-misuse analysis was degraded. Before installing, consider that the documented installer is unpinned and that scanners flagged a possible mismatch between installation guidance and the stated editing purpose.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied shell command installs a skill rather than examining prose, checking for missing inputs, or producing viewpoint corrections. Although the repository name suggests a related writing tool, its contents and behavior are not supplied. The visible installation behavior is materially different from the declared editing workflow.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The installation command uses an unpinned npm executable and an unpinned skill repository, creating a supply-chain risk if their upstream contents change or are compromised. This is not an MCP server reference or evidence of malicious behavior, but running the command can execute externally supplied code with the installer’s privileges.

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 40)May include surrounding context.

md
## Source and license

The public [story-skills scene-craft skill](https://github.com/danjdewhurst/story-skills/blob/main/skills/scene-craft/SKILL.md) informed the product category only. This repository's instructions, workflow, and examples are original and copy no external text or code. 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 40)May include surrounding context.

md
## 来源与许可

业务定位参考了 [story-skills / scene-craft](https://github.com/danjdewhurst/story-skills/blob/main/skills/scene-craft/SKILL.md) 的公开写作技能方向;本仓库的说明、流程与样例均为原创,未复制其文本或代码。仓库采用 [MIT License](LICENSE)。

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The documented installation command does not pin either the npm CLI version or the skill repository revision. Although this is ordinary installation guidance rather than an MCP configuration, compromised or changed upstream content could lead to execution of unreviewed code or installation of altered agent instructions.

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