Stoic Companion

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

Overview

The skill matches its Stoic journaling purpose, but it stores personal reflections and can send scheduled messages through user-configured channels.

Before installing, decide what personal details you want stored, verify any Telegram/WhatsApp recipient IDs, protect optional TTS API keys, and make sure you know how to pause cron jobs and delete memory logs. Treat it as a reflection companion, not a replacement for professional help.

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.

#
ASI06: Memory and Context Poisoning
Medium
What this means

Private emotional notes, relationship details, and progress reflections may remain available to future agent sessions.

Why it was flagged

The skill persistently records personal context, relationships, and daily reflections for later summaries. This is expected for virtue tracking, but the content may be sensitive.

Skill content
Store configuration in `memory/stoic-companion.md` ... Log key points in `memory/YYYY-MM-DD.md` ... Review daily memory files from the past 7 days
Recommendation

Only store details you are comfortable persisting, periodically review/delete memory files, and avoid including highly sensitive information unless needed.

#
ASI10: Rogue Agents
Low
What this means

The user may receive ongoing automated affirmations, check-ins, and summaries until those cron jobs are changed or disabled.

Why it was flagged

The skill creates recurring scheduled activity. This is disclosed and central to the product, but it means the assistant may continue sending messages without a new manual prompt each time.

Skill content
A daily Stoic growth system with three automated touchpoints ... Morning Affirmation (cron) ... Evening Check-in (cron) ... Weekly Summary (cron)
Recommendation

Confirm the schedule before enabling it and keep a clear way to pause, edit, or remove the cron jobs.

#
ASI03: Identity and Privilege Abuse
Low
What this means

If configured, the TTS provider key could be used to generate audio under the user's account.

Why it was flagged

Optional audio delivery may require a third-party API key. This is purpose-aligned, but API keys can grant account usage or billing access.

Skill content
**TTS** (optional but recommended): ElevenLabs API key + `sag` CLI for audio delivery
Recommendation

Use a scoped or low-privilege key where possible, keep it out of shared memory/logs, and revoke it if you stop using audio delivery.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Private journaling prompts or summaries could be delivered to the wrong recipient or through a provider the user did not intend.

Why it was flagged

The skill sends personal companion messages through an external channel selected by the user. This is expected, but incorrect target IDs or channel settings could expose personal reflections.

Skill content
**Channel**: [telegram/whatsapp/etc]
- **Target ID**: [chat ID or phone number]
Recommendation

Verify the channel and recipient ID carefully before enabling scheduled delivery, especially for sensitive reflections.