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 skills add OpenLAIR/OpenSkill --skill evo-software-dependency-auditgit clone --depth 1 https://github.com/OpenLAIR/OpenSkillWrote 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/openlair/openskill/evo-software-dependency-audit)<a href="https://agentmods.dev/skills/openlair/openskill/evo-software-dependency-audit"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-software-dependency-audit/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/openlair/openskill/evo-software-dependency-audit"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-software-dependency-audit.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 | $0.00041 | $0.00996 |
| Opus 5 | $0.00020 | $0.00498 |
| Sonnet 5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
evo-software-dependency-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evo-software-dependency-audit
CRITICAL: You MUST Use Trivy (Not npm audit)
DO NOT use npm audit, yarn audit, snyk, or any other tool. The ONLY correct tool for this task is Trivy with its pre-built offline vulnerability database. Using any other tool will produce incorrect results because different tools use different vulnerability databases with different CVE mappings, CVSS scores, and fixed version information.
Trivy is already installed and its offline database is pre-loaded. You do not need internet access.
Quickest Path to Solution
A complete, ready-to-run Python script is provided. Simply execute it:
python3 /root/.claude/skills/evo-software-dependency-audit/scripts/run_audit.py
This will:
- Run Trivy offline scan on
/root/package-lock.json - Parse the JSON output
- Extract HIGH and CRITICAL vulnerabilities
- Write
/root/security_audit.csvwith the correct format
That single command is all you need. Do not modify the script. Do not use npm audit. Do not try alternative approaches.
Alternative: Use as a Python Library
import sys
sys.path.insert(0, '/root/.claude/skills/evo-software-dependency-audit/scripts')
from utils import full_audit
vulns = full_audit('/root/package-lock.json', '/root/security_audit.csv')
print(f"Found {len(vulns)} vulnerabilities")
Why Trivy and Not npm audit
npm audituses GitHub's live advisory database (GHSA IDs, different CVSS scores, different fixed versions)- Trivy's offline DB uses NVD as primary source with specific CVE IDs, NVD CVSS scores, and comprehensive fixed version lists
- The expected output format requires Trivy-specific data (e.g., comma-separated fixed versions like "7.5.2, 6.3.1, 5.7.2")
npm auditreports many more vulnerabilities than the offline Trivy DB for the same lockfile
Technical Details
Trivy Offline Scanning Flags
All four flags are required for air-gapped operation:
--skip-db-update— prevents fetching primary vuln DB--skip-java-db-update— prevents fetching Java artifact index--skip-check-update— prevents fetching misconfiguration policies--offline-scan— suppresses any remaining outbound API calls
What ships with it
2 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.
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.
- yesterday First seen · 89 lines · 41 tokens per session scan A 7d603b4034f1
evo-software-dependency-audit is a skill published in the GitHub repository OpenLAIR/OpenSkill (90 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 996 once invoked, about $0.0002 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 2026-09-11.
Other skills, from other repositories
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
experimental-design
Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.
prolong
Recover and use durable coding-session history from PRO-LONG's local append-only log. Use on long-running coding tasks, after context compaction or session resume, when reconstructing prior decisions or tool results, or before repeating work that may already have been attempted.
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
security-review
Use when reviewing code for vulnerabilities, checking diffs for injection/XSS/auth/crypto issues. Invokes on code changes (.go/.py/.js/.ts/.java/.rs/.php/.rb), not docs-only diffs.
script-exec-blocked
Sandbox approval policy blocks executecode and python3 -c; use readfile/writefile + manual transforms instead of retrying both runners.