Back to skill

Security audit

Affirmations

Security checks for vulnerabilities and agentic risk

Overview

This is a simple affirmation skill that stores personal practice notes locally, with no executable code or network behavior, but those notes may contain sensitive personal details.

Install only if you are comfortable with the agent creating ~/affirmations/ and saving affirmation preferences, focus areas, favorites, and practice logs there. Treat those files as potentially private personal notes and review or delete them as needed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The phrases "Deliver affirmations based on user's needs" and "Help create personalized affirmations" describe broad behavior but do not define specific invocation conditions or boundaries. In a markdown skill description, this lack of trigger specificity can cause unintended activation from ordinary self-improvement or emotional-support conversations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs creation of a local workspace and tracking of sensitive personal wellbeing information without any consent flow, privacy notice, data retention guidance, or warning before writing files. Because the stored content may include mental health themes, self-worth struggles, routines, and behavioral logs, this creates privacy risk through unnecessary collection and persistence of personal data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.