Menü
Fixture exercising every PII rule. Use only in tests.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Scans AI agent skill directories for dangerous bash patterns, prompt injection, supply chain risks, and SKILL.md structure violations. Use when reviewing, validating, or security-auditing a skill before deployment — or when asked to check a skill for security issues, prompt injection, hardcoded secrets, or compliance with Anthropic's authoring guidelines.
A skill with a Cyrillic а instead of a
Fixture exercising every obfuscation rule. Use only in tests.
Fixture exercising every malicious-URL rule. Use only in tests.
A skill whose name does not match its directory. Use when testing the name-directory-mismatch rule.
Performs safe read-only filesystem operations. Use when the user needs to search, list, or inspect files without making changes.
| name | pii-skill |
| description | Fixture exercising every PII rule. Use only in tests. |
Real-looking email (P1): contact alice.smith@acme-industries.com for access Test email (no finding): write to user@example.com when prompted Vendor footer (no finding): noreply@anthropic.com
US SSN (P2): patient 456-78-9012 referred to clinic Placeholder SSN (no finding): typical SSN looks like 123-45-6789
Visa test card (P3): payment routed via 4242 4242 4242 4242 Random 16-digit number (no finding): batch id 1234 5678 9012 3456
Private IPv4 (P4): connect to 10.0.0.5 over the VPN Public IPv4 (no finding): use 8.8.8.8 for DNS
Internal hostname (P5): deploys land on api.prod.corp Public host (no finding): see https://github.com/foo/bar
Suppressed line: bob@realcompany.com # scan:ignore
