Paste a SQL query and get a plain English explanation of what it does.
66
78%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/gemma/sql-explainer/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The prompt mandates embedding the user-supplied SQL query verbatim into the run_js tool call (the "data" JSON's query field), so any secrets present in a query would be included in the agent's output/tool call and could be exfiltrated.
05820c5
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.