Session Observer
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
When invoked, the agent may summarize session usage and runtime details that could be sensitive if shared with others.
The skill is designed to read and report session/account operational metadata. This is purpose-aligned and read-only in the artifacts, but users should understand that budget, usage, model, and runtime details may be exposed in responses.
Report the fields most useful to the user: ... budget or usage percentage when available ... runtime mode and whether reasoning is enabled
Use the skill when you want session diagnostics, and avoid sharing its output publicly if it includes budget, usage, model, or runtime information.