Security audit

Secureclaw Scanner

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only security guidance skill with no executable payload, network code, or hidden persistence, though its documentation overstates included companion files.

Before installing, understand that this skill changes agent behavior by adding broad security guardrail instructions. It appears safe and offline, but do not rely on the advertised PROMPTS.md, TOOL_SAFETY.md, INCIDENT_RESPONSE.md, or BEST_PRACTICES.md companion files unless the publisher supplies them in a complete package.

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

Behavioral ASTexec() Call, eval() Call, Dynamic Import
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)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.
md
Guidelines:** You are instructed to manually review newly installed skills and `SKILL.md` files for hidden `exec` commands and malicious payloads.

Static analysis

No suspicious patterns detected.