ClawHub
Back to skill

Security audit

Security embedded Dev

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only defensive checklist for reviewing AI model supply-chain risks, with no hidden execution, persistence, or data export behavior found.

Installers should expect this skill to read project files relevant to ML model supply-chain review. It appears appropriate for authorized defensive assessments and does not request execution, write access, credentials, or persistence.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
90% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 423)May include surrounding context.

md
| OWASP Top 10 for LLMs (2025) | LLM03 | Supply Chain Vulnerabilities -- risks from third-party models, training data, plugins, and deployment dependencies |
| SLSA v1.0 | Build L0-L3 | Supply-chain Levels for Software Artifacts -- framework for assessing build/training pipeline integrity |
| MITRE ATLAS | AML.T0010 | ML Supply Chain Compromise -- adversary introduces compromised ML artifacts |
| MITRE ATLAS | AML.T0020 | Poison Training Data -- adversary manipulates training data to alter model behavior |
| MITRE ATLAS | AML.T0043 | Craft Adversarial Data -- adversary creates inputs designed to cause misclassification or misbehavior |
| NIST AI RMF 1.0 | MAP 2.3 | Scientific integrity and data quality in AI system lifecycle |
| NIST AI RMF 1.0 | GOVERN 1.5 | Ongoing monitoring and periodic review of the risk management process and its outcomes (applied here to third-party AI component risks) |

Static analysis

No suspicious patterns detected.