skills/ericrisco/rsc-harness/backups/Gen Agent Trust Hub

backups

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides strategic and technical guidance on backup and disaster recovery. It adheres to industry best practices like the 3-2-1-1-0 backup rule.
  • [COMMAND_EXECUTION]: The skill contains a shell script scripts/verify.sh. Analysis shows it is a read-only linter that uses grep to check for the presence of specific keywords (RPO, RTO, etc.) in user-provided documentation. It does not perform any dangerous file modifications or network operations.
  • [EXTERNAL_DOWNLOADS]: The skill references standard database tools (pgBackRest, WAL-G, XtraBackup, restic, BorgBackup) and cloud provider CLI commands (AWS CLI). These are well-known, industry-standard tools for the stated purpose. No downloads from untrusted sources are initiated.
  • [PROMPT_INJECTION]: No attempts to bypass safety filters or override agent behavior were found. The instructional language is focused on technical implementation and auditing.
  • [CREDENTIALS_UNSAFE]: The skill contains configuration templates and CLI examples. All sensitive fields (passwords, keys, bucket names) use placeholders like my-pgbackrest-backups or ..., following safe practice for template distribution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:36 PM
Security Audit — agent-trust-hub — backups