Back to skill

Security audit

Chronicler

Security checks for vulnerabilities and agentic risk

Overview

This skill openly aims to turn private session transcripts into publish-ready content, but it does so through broad transcript access and a recurring cron job that need clearer limits and controls.

Review this carefully before installing. Only use it on session history you are comfortable sending to the configured model and turning into draft public content. Prefer selecting or copying a narrow, sanitized transcript range, review every generated dispatch before posting, and make sure you know how to list and remove the cron job and the chat-memory dependency's scheduled tasks.

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
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T06 · System Persistence

Error
Location
SKILL.md:156
Finding

Recurring Cron Job Establishes Persistent Transcript Processing

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:116
Finding

Broad Processing of Sensitive Session Transcript Archives

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:21
Finding

Unpinned External Skill Dependency with Transcript Access

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction "Language: English. Always. No exceptions." imposes a fixed language policy with no opt-in, override, or region-specific justification. This violates the stated policy requirement against forcing a specific language or locale without user choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill sets up an automated cron job that repeatedly reads conversation transcripts from memory/sessions and turns them into publish-ready content, but the user-facing description does not prominently warn that private session history will be processed on a recurring basis. This creates a meaningful privacy and consent risk because users may install or enable it without realizing ongoing transcript ingestion and secondary use are core behaviors.

Content

No source excerpt is available for this finding.