Learning Evolution
AdvisoryAudited by Static analysis on May 11, 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.
Running the commands will execute local scripts and create or overwrite dated report files for the named skill.
The skill asks the user to run local shell scripts. This is disclosed and central to the skill's purpose, and the scripts only create local Markdown templates.
./scripts/analyze-usage.sh --skill <name> --period 30d
Run the scripts only from the installed skill directory and review LEARNING_DATA_DIR if you want reports saved somewhere specific.
If sensitive feedback or usage information is entered into the generated reports, it may remain on disk and be reused in later reviews.
The generated reports are intended to be filled with usage logs, feedback, and observed outcomes, which could become persistent local records if the user adds sensitive details.
Keep sensitive user feedback out of persisted reports unless retention is intentional.
Redact or anonymize sensitive user information before saving it in reports, and store reports only in an appropriate local directory.