arrow_backAI Skill ShieldpublicDefault-branch GitHub scan
Trust report
JuliusBrussee/caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
View scanned commit on GitHubopen_in_new0%Static score
60% score40% score gap
Highest finding: Critical severityLatest scan
critical severity
Static analysis score
Install decision
Do Not Install
Automatic execution surfaces were detected with critical or compounding risk. Hold installation until a reviewer clears the repo.
Scan identity
- Scanned
- 2026-08-08
- Commit
- 14d4f2e21a16
- License
- MIT
- Repository
- Active
Repository scan summary
- policyFindings
- 81
- terminalInstall surface
- 11
- Repository reach
- 96,746
Validation findings detected
Execution paths reviewed
GitHub stars
Highest-priority findings
The latest default-branch scan, ordered by severity.
- criticalDatabase drop/delete commandplugins/caveman/skills/caveman/SKILL.md:82
- criticalDatabase drop/delete commandskills/caveman/SKILL.md:82
- mediumMissing introductionplugins/caveman/skills/cavecrew/SKILL.md
- mediumNo agent compatibility detectedplugins/caveman/skills/cavecrew/SKILL.md
- mediumNo agent compatibility detectedplugins/caveman/skills/caveman-compress/SKILL.md
Share this trust result
The badge stays linked to the latest default-branch scan for this skill path.
Do you consider this skill safe to use?
Community signals help prioritize human review; they do not change the scan verdict.
AI Skill Shield is an automated pre-install review, not a guarantee of safety. Confirm sensitive permissions and execution paths before installation.