skills/go-sphere/skills/ent-seed-sql/Gen Agent Trust Hub

ent-seed-sql

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a template for generating and executing a Python script at runtime via a shell heredoc (python3
  • <<'PY') to create password hashes for seed data. This constitutes dynamic execution of generated code.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted inputs from prompts and external documentation to generate SQL and drive script generation.
  • Ingestion points: Documentation, demo code, and user prompts are identified as primary sources in 'SKILL.md'.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the source documents.
  • Capability inventory: The skill is authorized to execute Python scripts and perform file write operations for SQL output.
  • Sanitization: There is no evidence of validation or sanitization procedures for the external content before it is interpolated into the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 08:34 AM