Security audit

Durable Files Weekly Review (Public)

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed local documentation audit and writes a report, with cleanup actions gated on user approval.

Install this if you want a local audit of durable instruction files. Run it only against a workspace you intend to review, check the generated report before acting, and approve cleanup edits explicitly rather than allowing broad automatic changes.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill instructs users to run a local Python script that scans workspace files and can write reports, but the manifest does not declare any explicit tool scope or permissions. This creates a capability/expectation mismatch: an agent or reviewer cannot easily tell from the skill metadata that filesystem read/write access is required, which can lead to overbroad execution in sensitive workspaces.

Static analysis

No suspicious patterns detected.