skill-improver
What this skill does
The skill-improver is a utility designed to apply improvements to Claude Skills based on plans generated by `skill-quality-reviewer`. It reads improvement plan files, parses changes, executes updates,
github/galaxy-dawn - File System Access - 5.1k stars
Threat analysis
Skill info
pkg:github/Galaxy-Dawn/claude-scholar@2f7766f?skill=skill-improverAssessments (2)
File System Access
File System Access via local-llm-review
scripts/backup-skill.sh
The script backs up skill files by copying them to a backup directory. This could be a risk if the skill is not properly scoped or if the backup directory is not secured.Command Execution
Command Execution via local-llm-review
scripts/verify-update.sh
The script uses `yq` for YAML validation and relies on external commands. If not properly secured, this could be exploited if the script is manipulated.Badge
Add the Anomity scan badge for skill-improver to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of skill-improver? Report an issue or request a rescan.
