Menu
Project-specific security pass — secrets, personal data, path traversal, LLM tool whitelist.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/SandroHub013/UnaBetting --skill security-reviewThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| name | security-review |
| description | Project-specific security pass — secrets, personal data, path traversal, LLM tool whitelist. |
Run these checks on the pending diff/branch, in order:
github_pat_, sk-, API key values, .env
content. .env itself must never be staged.betanalytix.db*, reports/screenshots/, *.mp4 renders
are gitignored; if one is tracked or staged, stop and flag it._safe_path (src/dashboard/data_api.py); reject bypasses./ws/run stays whitelist-only; /ws/term is arbitrary-exec by design but
must remain local-only.src/dashboard/chat.py) needs explicit human sign-off._extract_runtime_bundle (zip-slip containment + sha256 manifest check,
validate-all-then-write; tests in tests/test_updater.py); any change to
/api/update/* or scripts/build_release_bundle.py re-runs those tests.Report each finding as: file:line → severity → concrete fix. Sensitive findings go in a private report, never a public issue.