Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/netresearch/security-audit-skill/security-auditnpx skills add netresearch/security-audit-skill --skill security-auditgit clone --depth 1 https://github.com/netresearch/security-audit-skillWrote 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/netresearch/security-audit-skill/security-audit)<a href="https://agentmods.dev/skills/netresearch/security-audit-skill/security-audit"><img src="https://agentmods.dev/badge/skills/netresearch/security-audit-skill/security-audit.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.00977 |
| Opus 5 | $0.00030 | $0.00489 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
security-audit scanned grade A with 0 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- checkpoints.yaml 143 KB
- evals/evals.json 17 KB
- references/api-key-encryption.md 7.3 KB
- references/api-security.md 49 KB
- references/authentication-patterns.md 35 KB
- references/automated-scanning.md 20 KB
- references/aws-security.md 18 KB
- references/ci-security-pipeline.md 20 KB
- references/cryptography-guide.md 33 KB
- references/cve-patterns.md 44 KB
- references/cvss-scoring.md 10 KB
- references/cwe-top25.md 16 KB
- references/deserialization-prevention.md 20 KB
- references/error-message-sanitization.md 10 KB
- references/file-upload-security.md 37 KB
- references/frontend-security.md 31 KB
- references/gha-security.md 2.9 KB
- references/git-history-secrets.md 4.5 KB
- references/go-security-features.md 26 KB
- references/iac-security.md 38 KB
- references/indistinguishability-defences.md 4.4 KB
- references/input-validation.md 25 KB
- references/javascript-typescript-security-features.md 35 KB
- references/llm-security.md 46 KB
- references/modern-attacks.md 38 KB
- references/nodejs-security-features.md 31 KB
- references/owasp-top10.md 7.6 KB
- references/path-traversal-prevention.md 25 KB
- references/php-security-features.md 22 KB
- references/python-security-features.md 35 KB
- references/react-security.md 18 KB
- references/security-headers.md 25 KB
- references/security-invariants.md 10.0 KB
- references/security-logging.md 36 KB
- references/supply-chain-incident-response.md 13 KB
- references/supply-chain-security.md 23 KB
- references/symfony-security.md 9.3 KB
- references/typo3-fluid-security.md 12 KB
- references/typo3-security.md 20 KB
- references/typo3-typoscript-security.md 12 KB
- references/vue-security.md 17 KB
- references/xxe-prevention.md 10 KB
- scripts/github-security-audit.sh 9.7 KB runs code
- scripts/scanners/android.sh 6.3 KB runs code
- scripts/scanners/aws.sh 4.9 KB runs code
- scripts/scanners/common.sh 1.7 KB runs code
- scripts/scanners/csharp.sh 5.6 KB runs code
- scripts/scanners/drupal.sh 4.9 KB runs code
- scripts/scanners/go.sh 6.4 KB runs code
- scripts/scanners/ios.sh 6.7 KB runs code
- scripts/scanners/java.sh 6.0 KB runs code
- scripts/scanners/javascript.sh 9.0 KB runs code
- scripts/scanners/joomla.sh 3.7 KB runs code
- scripts/scanners/nodejs.sh 8.9 KB runs code
- scripts/scanners/php.sh 16 KB runs code
- scripts/scanners/python.sh 8.3 KB runs code
- scripts/scanners/secrets.sh 5.9 KB runs code
- scripts/scanners/wordpress.sh 5.6 KB runs code
- scripts/security-audit-dispatcher.sh 6.1 KB runs code
- scripts/security-audit.sh 16 KB runs code
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.
- today Changed 0909e413a190
- 4d ago First seen · 68 lines · 61 tokens per session scan A da6891cb7a6e
security-audit is a skill published in the GitHub repository netresearch/security-audit-skill (40 stars, last pushed today), with no licence file. It adds 61 tokens to every session and 977 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sanctuary
Security, custody, and privacy infrastructure for AI agents. Use when the agent needs encrypted state storage, self-custodied identity, selective disclosure, zero-knowledge proofs, portable reputation, sovereignty health reporting, handshakes, MCP-to-MCP federation, protection-posture auditing, or principal dashboard…
git-workflow
Use when establishing branching strategies, implementing Conventional Commits, creating or reviewing PRs, resolving PR review comments, merging PRs (including CI verification, auto-merge queues, and post-merge cleanup), managing PR review threads, merging PRs with signed commits, handling merge conflicts, verifying a…
skill-repo
Use when creating skill repositories, standardizing or validating skill repo structure, setting up composer/release workflows, configuring split licensing (MIT + CC-BY-SA-4.0), fixing plugin.json / SKILL.md validation or version-parity errors, or releasing a skill version (version bump, tagging).
go-development
Use when developing Go applications, implementing job schedulers or cron (netresearch/go-cron, ofelia), Docker API integrations, LDAP/AD clients, building resilient services with retry logic, setting up Go test suites (unit/integration/fuzz/mutation), or running golangci-lint.
typo3-extension-upgrade
Use when an extension has to work with a newer or the current TYPO3 LTS, when a version bump breaks compatibility or leaves deprecated APIs behind, when upgrading v11->v12, v12->v13 or v13->v14 (v14.3 LTS is the current target), when one codebase must stay compatible with two versions, when running Extension Scanner…
github-project
Use when bootstrapping a repo (apply branch protection before first PR), PRs won't merge or BLOCKED, AI reviewer pushback, auto-merge fails for Dependabot/Renovate, branch protection or rulesets, CI fails, authoring or consuming reusable workflows, editing a repo's own .github/workflows, harden-runner, or…