Security audit

LintLang

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped helper for running a pinned static linter on user-selected agent instruction files.

Before installing, be aware that the skill can run a local linter over prompt and instruction files you choose, and uvx may download the pinned lintlang package once if it is not already installed. It is scoped to reporting lint findings and does not ask to modify your files automatically.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.
md
itself (`AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, `SKILL.md`, `agent.yaml` /

Rp1

Medium

Category: MCP Rug Pull
Confidence: 65% confidence
Finding: uvx/uv tool run commands without ==version create a rug-pull risk.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.