security-review

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By danielvm-git/bigpowers (GitHub) · coding · 288 stars · scanned at commit c19edc7

AI-powered security analysis of code changes — traces data flow, detects injection, auth bypass, secrets exposure, and unsafe deserialization across files. Use when reviewing pending changes, before release-branch, during verify-work Phase 5, during build-epic Step 0 threat modeling, or when the user says "security review" or "scan for vulns".

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this. Expected for a coding skill.

Found in 5 places.

skills/security-review/REFERENCE-confidence-rubric.md, line 16- `os.system(f"rm {user_path}")` where user controls the path
skills/security-review/REFERENCE-vuln-categories.md, line 39| **Vulnerable** | User input in shell commands: `os.system(f"ping {host}")`, `subprocess.run(f"grep {pattern} file", shell=True)` |
skills/security-review/REFERENCE-vuln-categories.md, line 40| **Safe** | `subprocess.run(["ping", host])` with arguments as list; `shlex.quote()` |

Show 2 more

skills/security-review/REFERENCE-vuln-categories.md, line 41| **Look for** | `shell=True`, `os.system`, `os.popen`, `exec()`, `eval()`, `$()`, backticks |
skills/security-review/SKILL.md, line 35bash scripts/lib/parallel-review-worktrees.sh security-review

Connects to the internet

The author does not mention this.

Found in 2 places.

skills/security-review/REFERENCE-vuln-categories.md, line 31| **Vulnerable** | User-controlled URL passed to server-side HTTP client: `requests.get(user_url)` |
skills/security-review/REFERENCE-vuln-categories.md, line 33| **Look for** | User input → `fetch`, `requests.get`, `axios.get`, `urllib`, `curl`, `http.get`; host control only (path-only is excluded) |

Other copies in this repository

danielvm-git/bigpowers has 3 more folders with a skill named security-review. This page shows the lowest-scoring copy.

.pi/skills/security-review 94/100 · Low risk
.cline/skills/security-review 94/100 · Low risk
.gemini/extensions/bigpowers/skills/security-review 94/100 · Low risk

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'security-review' ] || [ -L ~/.agents/skills/'security-review' ]; then echo 'A skill folder named security-review already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/danielvm-git/bigpowers' "$d" && git -C "$d" checkout --quiet 'c19edc76adb8363921bc3edb4a410216b63d9618' -- 'skills/security-review' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/security-review' ~/.agents/skills/'security-review' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'security-review' ~/.claude/skills/'security-review' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for danielvm-git/bigpowers shows the score of its lowest-scoring skill.

SkillTrust badge for danielvm-git/bigpowers

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/danielvm-git/bigpowers.svg)](https://zalavijaysinh.github.io/skilltrust/repos/danielvm-git/bigpowers/)

Score history

Date	Version	Score
2026-11-09	`c19edc7`	90
2026-11-07	`9b9a662`	100