Security audit

Sed Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a small text-editing skill whose file-changing behavior is expected for a sed-style tool, though users should be careful with in-place edits.

Use preview-style commands before using `-i` on important files, and keep backups when applying broad replacements across multiple files.

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

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 (1)

Medium

Confidence: 90% confidence
Finding: This markdown file documents the `-i` option and provides an in-place editing example, but it does not warn users that the operation directly changes file contents and may overwrite data. Because the skill description includes behavior that can affect user data, a brief disclosure about destructive or irreversible effects is expected.

No suspicious patterns detected.