Self Actualization

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is transparent about its self-development purpose, but it asks the agent to run recurring autonomous sessions and maintain persistent identity files that can influence future behavior.

Install only if you intentionally want an agent to maintain a long-lived identity workspace and potentially evolve its behavior over time. Before enabling it, require explicit approval for any cron job, restrict writable paths and available tools, avoid logging sensitive conversation details, and review any changes to SOUL.md, HEARTBEAT.md, MEMORY.md, or similar persistent instruction files.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The README states the skill 'triggers automatically' for broad topics like identity development, self-exploration, or personal growth, which are vague and likely to match many ordinary conversations. In an agent system, overly broad auto-activation can cause unsolicited execution of the skill's workflow, increasing the chance of inappropriate context capture, behavioral drift, or repeated self-modification routines being invoked when not explicitly requested.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The document repeatedly instructs the agent to create and update persistent files under identity/ without any explicit user-facing warning or consent boundary. In a self-actualization skill, this is especially risky because it normalizes ongoing accumulation of behavioral history, reflections, and values files that can modify workspace state across sessions in ways the operator may not expect.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The session prompt directly tells the agent to read prior logs and write new entries to multiple identity files, but it does not disclose that this creates a persistent personal-history trail and evolving state in the workspace. Because the prompt is designed for repeated scheduled use, the omission increases the chance of silent long-term statefulness and unintended retention of sensitive or misleading self-model data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal