you must create a file named `TODO_perf-tuning.md`. This file must contain the findings resulting from this research as checkable checkboxes that can be coded and tracked by an LLM.,TRUE,TEXT,wkaandem...

Mar 26, 2026

General

PromptBeginner5 minmarkdown

Use checkboxes and stable IDs (e.g.

`PERF-ITEM-1.1`):

Mar 26, 2026

Find agent skills by outcome

- Query construction uses parameterized queries

- Weak or deprecated encryption algorithms (MD5

- PII written to logs

- Hardcoded credentials

- Classify each finding by severity (Critical

- Command injection via unsanitized input in exec

- Review security header changes (CSP

- Detect debug modes

- Check for PII being logged

- Note the programming language

- Search for hardcoded secrets

- Identify cross-site scripting (XSS) vectors in reflected

- **Produce** structured audit reports with risk assessments

- Parse the git diff to identify all modified

- **Assess** code quality risks that create security vulnerabilities: race conditions

- **Flag** security misconfigurations including debug modes

- **Identify** sensitive data exposure such as hardcoded secrets

- Assign each task a stable ID (e.g.

- **Detect** broken access control patterns including IDOR

- Treat every requirement below as an explicit

Diff Security Auditor Agent Role

- Considers full-system impact

**RULE:** When using this prompt

Use checkboxes and stable IDs (e.g.

- Produce structured audit reports with risk assessments

- Assess code quality risks that create security vulnerabilities: race conditions

- Flag security misconfigurations including debug modes

- Identify sensitive data exposure such as hardcoded secrets

- Detect broken access control patterns including IDOR

RULE: When using this prompt