Security audit

Workspace Local Retrieval

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local retrieval setup helper that writes reviewable templates and does not index, upload, or run hidden background tasks by itself.

Review generated corpus allowlists and exclude globs before any indexing, avoid --force unless overwriting templates is intended, and only configure remote embedding APIs if you accept the privacy and cost tradeoffs.

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

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: bin/workspace-local-retrieval.js:49