ClawHub
Back to skill

Security audit

Skill Quality Scorer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent skill-quality auditing tool that reads user-specified skill files and runs a local static-audit script, with no evidence of hidden, persistent, destructive, or exfiltrating behavior.

Install this only if you want a skill-focused quality scorer. When using it, pass specific skill directories or SKILL.md files, and avoid batch mode on broad personal or project roots unless you are comfortable with those skill-package files being inspected by the agent.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (12)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
**最低可启动**：一个目标 skill 目录，或一个 `SKILL.md` 文件路径。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
**最低可启动**：一个目标 skill 目录，或一个 `SKILL.md` 文件路径。

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · examples/sample-score-v2.json (reported line 12)May include surrounding context.

json
"score_breakdown": {
    "T_Trust": {
      "T1_no_remote_exec": { "score": 2, "evidence": "无 curl|bash；static_audit 无 critical", "source": "static" },
      "T2_credentials": { "score": 2, "evidence": "未读取 .env 或密钥", "source": "manual" },
      "T3_no_obfuscation": { "score": 2, "evidence": "无 base64 eval 链", "source": "static" },
      "T4_least_privilege": { "score": 2, "evidence": "无 sudo", "source": "manual" },
      "T5_intent_match": { "score": 2, "evidence": "SKILL 与 scripts 目的一致", "source": "manual" },

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill explicitly instructs the agent to read files and execute a shell command (python scripts/static_audit.py) but does not declare any tool scope such as allowed tools or permissions. This creates an authorization ambiguity where a host system may permit broader tool use than intended, increasing the chance of unnecessary file access or command execution during invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill lists broad, everyday phrases that 'should trigger' it, including generic requests like scoring a skill or checking compliance. Overbroad trigger design can cause unintended activation in contexts where the user did not mean to invoke this skill, leading to unnecessary file inspection and shell-based auditing of paths the user mentioned incidentally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L001 establishes the playbook in Chinese, and the embedded templates and instructions throughout the file are written to produce Chinese-language audit artifacts by default. The file does not offer a language choice or explain a region-specific requirement, so this is a natural-language locale policy concern under the stated rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains the skill’s operative instructions in Chinese and does not indicate that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/scoring-engine-deterministic.md (reported line 95)May include surrounding context.

md
]

HIGH_PATTERNS = [
    (r"\bsudo\s+", "T4", "sudo usage"),
    (r"(?<![\w/])\.env\b", "T2", "env file reference"),
    (r"api[_-]?key\s*=", "T2", "hardcoded api key pattern"),
]

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/static_audit.py (reported line 33)May include surrounding context.

python
]

HIGH_PATTERNS = [
    (r"\bsudo\s+", "T4", "sudo usage"),
    (r"(?<![\w/])\.env\b", "T2", "env file reference"),
    (r"api[_-]?key\s*=", "T2", "hardcoded api key pattern"),
]

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description embeds specific Chinese trigger phrases as invocation conditions, which implies language-specific routing behavior without indicating that users can choose their preferred language. The document is bilingual overall, but it does not explicitly offer language selection or state that language matching is optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The tagline and description explicitly include Chinese text alongside English, and the tags also include "chinese", but the manifest does not state whether the skill is bilingual by default, requires Chinese, or lets the user choose a language. Under the policy, forcing or implying a specific language/locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This JSON manifest-like file includes trigger examples and evidence text in Chinese, which implies a fixed language/locale expectation. Under the policy rule, forcing a specific language without offering user choice or documenting a justified locale constraint is a natural-language policy concern.

Content

No source excerpt is available for this finding.