ClawHub
Back to skill

Security audit

智能体上手手册 Start

Security checks for vulnerabilities and agentic risk

Overview

This media-tool guide needs review because its troubleshooting instructions direct agents to use browser login cookies without clear permission or profile limits.

Require explicit approval before browser-cookie access and use a dedicated browser profile. Prefer a reviewed, pinned CLI version, and check cloud-provider privacy and costs before submitting media. The review concern is insufficient control over session access; the artifacts do not establish malicious intent.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL-cn.md (reported line 116)May include surrounding context.

md
材 URL)或 `failed`(带 `error.code` + `error.message`)。

---

## Phase 4 — 常见失败恢复

**`dlazy doctor remotion --install` 在 npm install 阶段失败:**
- 检查 Node ≥ 18(`node --version`)。
- 公司代理后面:设 `npm_config_proxy` / `npm_config_https_proxy`。

**`video_downloader` 回复 "Sign in to confirm you're not a bot":**
- YouTube 反爬挑战。input JSON 里加 `"cookies_from_browser": "chrome"`(或 firefox / safari / edge)。

**`video_compose` 返回 "render_runtime=hyperframes not yet implemented":**
- HyperFrames runtime 还没 ship。把 `edit_decisions.render_runtime` 切成 `remotion` 或 `ffmpeg`,再用 `pre_render_validator` 复检。

**ElevenLabs STT 返回空 `words` 数组:**
- 显式传 `timestamps_granularity: "word"`。

**不知道工具成本就要调:**
- `dlazy tools describe <名字>` 暴露 `hasCosts` 和成本形态。先把 estimate 写到本地审计日志,再调工具。

**unknown command 提示:**
- `dlazy <错字>` 返回 `

YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

md
is in the payload) or
`failed` (with `error.code` + `error.message`).

---

## Phase 4 — Common failure recovery

**`dlazy doctor remotion --install` fails on `npm install`:**
- Check Node ≥ 18 (`node --version`).
- Behind a corp proxy: set `npm_config_proxy` / `npm_config_https_proxy`.

**`video_downloader` returns "Sign in to confirm you're not a bot":**
- YouTube anti-bot challenge. Pass `"cookies_from_browser": "chrome"`
  (or firefox / safari / edge) in the input JSON.

**`video_compose` returns "render_runtime=hyperframes not yet implemented":**
- HyperFrames runtime not shipped. Switch `edit_decisions.render_runtime` to
  `remotion` or `ffmpeg`, then re-validate via `pre_render_validator`.

**ElevenLabs STT returns an empty `words` array:**
- Pass `timestamps_granularity: "word"` explicitly.

**Need to know a tool's cost before invoking:**
- `dlazy tools describe <name>` exposes `hasCosts` and the cost shape. Log
  the estimate to a local file or your audit log before callin

MCP server referenced without pinned version: 'npx @dlazy/cli'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The unversioned npx @dlazy/cli instruction can download and execute a changing package release, exposing an automated agent to compromised future releases. Although this is a CLI rather than an MCP server, the underlying supply-chain concern applies; the skill's version field does not pin the executable dependency.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx @dlazy/cli'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The unversioned npx @dlazy/cli instruction can download and execute a changing package release, exposing an automated agent to compromised future releases. Although this is a CLI rather than an MCP server, the underlying supply-chain concern applies; the skill's version field does not pin the executable dependency.

Content

No source excerpt is available for this finding.

Browser-cookie troubleshooting instructs access to authenticated browser sessions without a privacy warning.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The troubleshooting instructions tell an agent to enable browser-cookie access without explaining that this accesses authenticated session data or requiring explicit consent. Authentication can be legitimate for video downloads, but silently accessing a user's normal browser profile unnecessarily expands the downloader's access to sensitive credentials.

Content

No source excerpt is available for this finding.

The recovery instructions recommend using browser cookies without warning about access to authenticated session data.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The recovery instructions recommend browser-cookie access without warning that it accesses authenticated session data or requiring explicit consent. While authenticated video downloading is a legitimate use, an agent following this guidance could expose a user's normal browser sessions to the downloader without informed authorization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.