Prompt file imported from gesh75/netlog-ai (
.github/prompts/review.prompt.md). Copyright stays with the author.
Review the current diff (git diff plus staged changes) and report findings ordered by severity.
Check, in this order:
- Secrets - hardcoded keys, tokens, passwords, connection strings, in code or tests.
- Injection - SQL/shell/path built by string concatenation from untrusted input.
- Boundary validation - external input used without validation.
- Error handling - swallowed exceptions, bare
except, missing failure paths. - Mutation - functions that modify their arguments in place.
- Size - functions over 50 lines, files over 800 lines, nesting deeper than 4.
- Test coverage - new behaviour with no accompanying test.
For each finding give: file:line, severity (CRITICAL/HIGH/MEDIUM/LOW), the concrete failure
scenario, and the minimal fix. If a category is clean, say so in one line - do not pad the report.