Sage Decision Journal
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This decision-journal skill is purpose-aligned, but it asks the agent to silently monitor every conversation and persist inferred personal/work decisions without clear limits or controls.
Install only if you are comfortable with an automatic decision journal that may monitor all conversations and save inferred personal or business decisions over time. Before using it, look for settings or instructions that let you opt in, pause capture, review/edit entries, delete history, and inspect the referenced sage-cognitive dependency.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
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.
Private or work-related choices may be captured automatically even when the user did not intend to journal that conversation.
This instructs the agent to operate as an always-on background monitor across conversations rather than only when the user explicitly asks for decision journaling.
The journal runs silently alongside sage-cognitive. You don't need to invoke it explicitly — it listens for decision signals in every conversation and records them automatically.
Require explicit user opt-in for automatic capture, provide a way to pause or disable monitoring, and ask for confirmation before saving sensitive or inferred decisions.
The agent may build a long-term profile of the user's decisions and reasoning, including inferred motives that the user did not explicitly state.
The skill directs persistent storage of inferred decision records, including reasoning, alternatives, context, and confidence, which can contain sensitive personal or business information.
Implicit decisions — inferred from behavior and context ... Every captured decision is stored with five fields: WHAT, WHY, ALTERNATIVES, CONTEXT, CONFIDENCE
Define storage location, retention, deletion, review/edit controls, and clear rules for when inferred decisions may be saved.
Past conversations may influence later guidance, and incorrect or sensitive records could persist and shape future analysis.
The skill uses accumulated records for later pattern analysis, indicating cross-session reuse of stored behavioral context without documented user controls or retention limits.
After 10+ decisions are logged, begin running pattern analysis. Surface patterns — don't diagnose them.
Let users inspect, correct, delete, and scope the decision history before it is reused for pattern analysis.
The reviewed artifacts do not show how the referenced profile is created, stored, or shared.
The skill declares a dependency on another skill whose artifacts were not provided, and the text says it builds on that other skill's identity and behavioral profile.
depends_on:
- sage-cognitiveReview the sage-cognitive skill separately before installing this one, especially its memory and profiling behavior.