arrow_backAI Skill ShieldpublicDefault-branch GitHub scan
Trust report
anthropics/skills
Public repository for Agent Skills
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
Critical security findings were detected. Hold installation and review the evidence before proceeding.
Scan identity
- Scanned
- 2026-08-08
- Commit
- f17010c9bb48
- License
- Not detected
- Repository
- Active
Repository scan summary
- policyFindings
- 125
- terminalInstall surface
- 2
- Repository reach
- 166,919
Validation findings detected
Execution paths reviewed
GitHub stars
Highest-priority findings
The latest default-branch scan, ordered by severity.
- criticalMulti-stage payload deliveryskills/claude-api/SKILL.md:1
- criticalMulti-stage payload deliveryskills/skill-creator/SKILL.md:1
- highAuto-confirm dangerous operationsskills/claude-api/SKILL.md:211
- highToken limit exceededskills/claude-api/SKILL.md
- highTrick user directiveskills/docx/SKILL.md:3
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.