db-engine-selection

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from user-provided workload descriptions which could be crafted to influence agent behavior.
  • Ingestion points: The skill processes user-supplied text describing access patterns, consistency requirements, and scale (SKILL.md).
  • Boundary markers: Absent; there are no instructions to the agent to utilize delimiters or to ignore embedded instructions within the user input.
  • Capability inventory: The skill's configuration enables access to powerful tools including Bash and WebFetch.
  • Sanitization: No sanitization, validation, or escaping of the user-provided workload description is mentioned or enforced in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 10:01 PM
Security Audit — agent-trust-hub — db-engine-selection