Security audit

Token Saving Mastery

Security checks for vulnerabilities and agentic risk

Overview

This advice-only token-saving skill is not malicious, but it gives under-scoped instructions to edit installed skills and automate session archiving, which can affect future agent behavior and access to history.

Install only if you treat it as manual optimization advice. Before following it, review every skill patch as a diff, back up or export anything you may need, avoid deleting safety or authentication instructions, and do not enable the session-cleanup cron until you know exactly what will be archived and how to restore or disable it.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill recommends automated archival and cleanup of session history, including a cron job, without warning users that this modifies access to historical conversations and may hide, remove, or make context harder to recover. In a productivity skill about token reduction, users are especially likely to apply the guidance broadly, so accidental loss of important conversational state or records becomes a realistic operational risk.

Static analysis

No suspicious patterns detected.