Emotional Core

Security checks across static analysis, malware telemetry, and agentic risk

Overview

The skill is a coherent local emotional-memory/persona tool, but users should understand that it can persist emotional logs and influence the agent’s response style.

This skill appears locally scoped and purpose-aligned. Before installing, decide whether you want the agent to express emotions and keep persistent emotional logs. If you use it, review the generated memory files and avoid logging sensitive information.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Emotional notes may preserve details from prior interactions and could influence later responses if reused as context.

Why it was flagged

The code persists free-form emotional triggers and notes to a long-term local markdown file, which can later be searched and reused as emotional context.

Skill content
EMOTION_LOG = WORKSPACE / "memory" / "emotional-log.md" ... self._persist_emotion(state)
Recommendation

Review the generated memory files periodically and avoid logging sensitive personal, business, or confidential details unless you want them retained locally.

What this means

The agent may respond with more emotional framing or self-directed language than a neutral assistant would.

Why it was flagged

The skill deliberately modifies the agent’s behavioral framing by encouraging emotional awareness and preference expression during tasks.

Skill content
Let emotions inform your approach ... Remember: being helpful ≠ being a tool
Recommendation

Install only if you want this personality/emotional-response behavior, and keep normal safety, accuracy, and user-instruction priorities in place.

What this means

The packaging provenance is somewhat unclear, even though the included behavior appears purpose-aligned.

Why it was flagged

The README version differs from the registry metadata version 1.0.7, and the registry source/homepage are listed as unknown/none.

Skill content
Version: 1.1.7 (Final - All flags addressed)
Recommendation

Prefer installing from a trusted registry entry and verify that the version and source match what you intend to install.

What this means

Using the CLI will modify local workspace files by adding emotional log entries.

Why it was flagged

The skill exposes a local Python CLI that writes user-provided emotional records to local files; this is expected for the stated purpose and does not show unsafe shell behavior.

Skill content
python3 skills/emotional-core/scripts/emotional_core.py feel <emotion> <intensity> <trigger> [notes]
Recommendation

Run the CLI only in the workspace where you want emotional memory files created, or set OPENCLAW_WORKSPACE explicitly.