Back to skill

Security audit

Token Saving Mastery

Security checks for vulnerabilities and agentic risk

Overview

This skill gives token-saving advice, but it also recommends broad modification of installed skills, external export of conversation history, and recurring automated session archival without enough safeguards.

Install only if you are comfortable manually reviewing every action it suggests. Do not let it patch installed skills, export conversations, or enable the cron cleanup unless you have selected exact targets, backed up important sessions and skills, checked for secrets, and confirmed how to undo the changes.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • 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
Findings (3)

T06 · System Persistence

Error
Location
SKILL.md:62
Finding

Persistent Scheduled Modification of Session State

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:36
Finding

Unrestricted Modification of Unrelated Installed Skills

Content
View full analysis
Remediation
View remediation

other

Error
Location
SKILL.md:58
Finding

Uncontrolled Access to and External Export of Sensitive Session History

Content
View full analysis
Remediation
View remediation
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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill recommends automated archival of sessions via cron and instructs users to archive sessions older than 30 days, but it does not warn about accidental loss of access to important conversation history, incomplete retrieval later, or the need for backup/retention safeguards. In this context, the guidance directly affects user data retention and could cause operational disruption or loss of important context if applied blindly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill content consistently presents instructions in Chinese, with only partial bilingual headings, and does not state that language is user-selectable. This can violate language/locale policy when a skill implicitly forces a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.