ClawHub
Back to skill

Security audit

Model Fingerprint Audit Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent model-auditing guide that uses authorized synthetic probes and clearly warns users not to expose API keys or private data.

Install only if you intend to audit model endpoints and are comfortable providing your own authorized API key source. Use low-cost pilot runs first, keep keys out of reports and committed files, confirm quota impact before full runs, and treat cached baselines as sanitized artifacts with clear provenance.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/baseline-sources.md (reported line 7)May include surrounding context.

md
| Claimed model | Candidate reference source | Expected model ID | Access note |
|---|---|---|---|
| Kimi K3 | https://api.moonshot.ai/v1 or NVIDIA NIM `https://integrate.api.nvidia.com/v1` | `kimi-k3` or provider-qualified K3 ID | Provider API key required |
| GLM-5.3 Flash | Z.ai / a documented GLM provider | `glm-5.3-flash` | Provider API key required |
| GLM-5.2 | Z.ai / a documented GLM provider | `glm-5.2` | Provider API key required |
| Qwen3.8-Max | Alibaba Cloud Model Studio / Qwen Cloud | `qwen3.8-max` | Provider API key required |

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow defines output labels exclusively in Chinese (符合, 可疑, 无法判断) in an otherwise English document. This imposes a specific language on users without opt-in or a documented locale-specific reason, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction to report 无法判断 mandates a Chinese output string without offering a language or locale choice. This is a natural-language policy issue because it forces a specific language regardless of user preference or context.

Content

No source excerpt is available for this finding.