Back to skill

Security audit

migrate-to-e2e

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious with medium confidence because its setup instructions include unpinned package downloads and it lacks a privacy warning for model-backed test observations; no malicious behavior was reported, and coverage is partial.

Review and pin the package versions and sources before running setup commands. Before enabling model-backed tests, consider whether screenshots or other application observations could contain sensitive information and where they may be sent. The scan is partial because referenced material was missing, so the evidence does not establish that the full skill and its references are safe.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (14)

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 · SKILL.md (reported line 23)May include surrounding context.

md
Two references do most of the work. Read them; do not restate them.

- The e2e skill for everything the runner does: `.agents/skills/e2e/SKILL.md`
  once `npx e2e init` or `npx skills add e2e-inc/e2e` ran, or
  `npx e2e guide <topic>` from the installed package. Topics named below
  (`setup`, `writing-tests`, `agent`, `mcp`, `running`, `debugging`) are its

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

npx skills add e2e-inc/e2e can execute an unpinned installer and imports additional agent instructions without specifying an immutable source revision. Compromise of either the installer release or the upstream skill could introduce executable code or adversarial instructions into the migration workflow.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx e2e'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The bootstrap instruction uses npx e2e init before a local installation is necessarily available, allowing npx to download and execute an unpinned registry release. A compromised release could execute with the agent's filesystem and environment access; this is a package supply-chain issue, not specifically an unpinned MCP server.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx e2e'.

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.

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

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.

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

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.

MCP server referenced without pinned version: 'npx e2e'.

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.

MCP server referenced without pinned version: 'npx e2e'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The harness bootstrap directs npx e2e init --yes when no e2e configuration exists, without first requiring a reviewed local package installation. If the dependency is absent, npx can resolve and execute a mutable registry release with the agent's privileges.

Content

No source excerpt is available for this finding.

Model-backed test execution lacks a privacy warning about sharing application observations with the configured model provider.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The skill asks the user to choose a model but does not explain that model-backed actions may transmit application observations, potentially including screenshots, personal data, or authenticated content, to that provider. Model selection and secret-storage precautions do not establish informed approval for this data transfer; deterministic execution being available limits the exposure.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx e2e'.

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.

MCP server referenced without pinned version: 'npx e2e'.

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.

MCP server referenced without pinned version: 'npx e2e'.

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.

MCP server referenced without pinned version: 'npx e2e'.

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.

MCP server referenced without pinned version: 'npx e2e'.

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.