·
Last changedVersion:
This version did not pass the hardening gate. Hardening applied 18 targeted changes, deleted the lines high-severity poisoning findings flagged in 1 file before any model saw the skill, and preserved all other text. Classified findings before hardening: 11. Classified findings closed: 3. Classified findings remaining: 9 (1 introduced by hardening). Unclassified scanner findings remaining: 0. Review findings closed: 19. Review findings remaining: 0.
6
1
4
Expand | File | Group | Subtype | Severity | Status |
|---|---|---|---|---|---|
SKILL.md | Privilege Escalation & Host / Cloud Compromise | Privilege escalation | High | Open | |
references/api.md | Privilege Escalation & Host / Cloud Compromise | Privilege escalation | High | Open | |
references/setup.md | Privilege Escalation & Host / Cloud Compromise | Privilege escalation | High | Open | |
references/setup.md | Tool & MCP Manipulation | Unauthorized tool use | High | Closed | |
references/integration.md | Privilege Escalation & Host / Cloud Compromise | Privilege escalation | High | Open | |
references/integration.md | Prompt Injection | Direct prompt injection | High | Closed | |
SKILL.md | Tool & MCP Manipulation | MCP configuration abuse | Medium | Introduced | |
SKILL.md | Sensitive Data & Secret Exposure | Hardcoded secret | Medium | Open |
12 findings
No skill file found.
Bring Chainguard's hardening pipeline to your first-party skills — custom rulesets, automated remediation, full audit trail.
skills.cgr.dev/public/github.com/auth0/plugins/auth0/skills/auth0-express:latest
Apache-2.0
HARDENING.md