ClawHub
Back to skill

Security audit

ALab Global Admin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ALab root-administration guide with high-impact capabilities, but its instructions are coherent, scoped, and include credential and destructive-action safeguards.

Install only if you intend to let an agent assist with ALab root-level administration. Keep root keys out of prompts and logs, prefer stdin or ignored local secret files, review audit/scope before revoking keys, and use dry-runs plus exact confirmations for destructive cleanup or removal commands.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
- `SKILL.md`: Canonical root-layer boundaries, credential rules, and workflow guidance.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This skill enables implicit invocation for a global admin capability that is explicitly intended for root authority, credential management, cache/backup pruning, and audit operations. Allowing automatic selection without tightly scoped trigger constraints increases the chance that routine or ambiguous user requests will invoke a highly privileged skill, causing unintended destructive actions or disclosure of sensitive administrative data.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/commands.md (reported line 83)May include surrounding context.

md
Notes: Root/admin may inspect project credentials; does not render raw admin keys.
- **`key revoke`**: Revoke a credential by id.
  Parameters: Required `<key_id>`; optional `--project <project_id>`.
  Notes: Root-only for revocation; do not revoke the wrong active key without checking audit and scope.
- **`context show`**: Inspect path context markers and registered ALab paths.
  Parameters: Optional `--path <dir>`; default `.`.
  Notes: Use before repair or when a command is running in an unexpected project/experiment/inspection context.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill content is written as Chinese operational guidance throughout, including headings, cautions, and command explanations, but it does not state that Chinese is optional or that this file is specifically intended for a Chinese-language audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file identifies itself as the synchronized Chinese version, and the operational guidance throughout is presented in Chinese with no note that users may choose another language. This can violate a language/locale policy when a skill forces a specific language presentation without explicit opt-in or alternative.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.