Back to skill

Security audit

复杂镜头拆分计划

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a clearly scoped shot-planning workflow, with only a routine caution about its unpinned installation command.

The skill needs only the scene material you provide. If using the documented installer, prefer a reviewed, pinned CLI version and source revision because the unpinned command can retrieve changing upstream code.

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 chunk is an installation command, not an implementation of the declared shot-breakdown workflow. It contains no processing of scene descriptions, plot constraints, duration budgets, or missing-input checks. The installed skill might provide those features, but its contents are not supplied and cannot be verified here.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The documented installation command invokes an unpinned npm package through npx, which can download and execute a changing release with the user's privileges. A compromised upstream release could therefore execute malicious code during installation; although the finding incorrectly describes the CLI as an MCP server, the underlying supply-chain exposure is real. This is installation documentation rather than an automatic execution instruction, which limits immediate exposure, and there is no evidence of malicious intent.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

The installation command uses an unpinned executable npm package, so npx may download and execute whichever version of skills is resolved at installation time. A compromised package release could execute code with the installing user's privileges; this is a supply-chain exposure, not evidence of malicious behavior. The scanner's MCP-server characterization is inaccurate—the README describes a CLI installation command—but the unpinned execution risk remains.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'Uvxp'.

Medium
Category
MCP Rug Pull
Confidence
65% confidence
Finding

uvx/uv tool run commands without ==version create a rug-pull risk.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

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