Inner Life Reflect
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only skill transparently keeps local reflection memory for the agent, with no evidence of credentials, network access, hidden code, or destructive behavior.
Before installing, be comfortable with the agent maintaining local reflection notes that may influence future behavior. Periodically inspect SELF.md and habits.json to remove inaccurate or unwanted self-model entries.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
65/65 vendors flagged this skill as clean.
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.
Incorrect or over-personal reflection entries could persist and shape later agent responses.
The skill reads local agent memory and diary content, then writes persistent self-reflection and habit files that may influence future behavior.
**Reads:** inner-state.json, habits.json, drive.json, diary (latest) **Writes:** SELF.md, habits.json (when patterns crystallize into habits)
Review memory/SELF.md and memory/habits.json periodically, and edit or delete entries that should not influence future sessions.
The agent may continue considering reflection updates over time rather than only when directly asked.
The skill defines a recurring reflection cadence. The behavior is disclosed and aligned with the skill's purpose, and the artifacts do not include hidden background code.
### Micro check (every 3 hours) Scan for hard/soft triggers. Does NOT auto-write — only decides if reflection is due.
Install only if you want ongoing self-reflection behavior, and disable or remove the skill if you do not want periodic memory updates.