database-backup

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to generate and execute shell scripts containing commands such as pg_dump, mongodump, tar, and find for managing database backups and retention policies.
  • [CREDENTIALS_UNSAFE]: Documentation examples include connection strings with dummy credentials (e.g., mongodb://backup_user:secret@rs1.example.com:27017). Although intended as placeholders, these patterns involve hardcoded sensitive fields in the provided templates.
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its architecture:
  • Ingestion points: User-provided database names, connection details, and storage paths are interpolated into shell scripts (described in the 'Usage' and 'Examples' sections).
  • Boundary markers: None identified in the provided instructions to delimit user input from shell command structures.
  • Capability inventory: The skill facilitates arbitrary shell script generation and execution through the agent's command capabilities.
  • Sanitization: There are no instructions for the agent to validate or escape user-supplied strings before using them in shell commands, potentially allowing for command injection if a user provides malicious database names or paths.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:01 PM
Security Audit — agent-trust-hub — database-backup