Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jayelbotvibe-web/hermes-pentest-labnpx agentmods add skills/jayelbotvibe-web/hermes-pentest-lab/pentest-findingsWrote 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/jayelbotvibe-web/hermes-pentest-lab/pentest-findings)<a href="https://agentmods.dev/skills/jayelbotvibe-web/hermes-pentest-lab/pentest-findings"><img src="https://agentmods.dev/badge/skills/jayelbotvibe-web/hermes-pentest-lab/pentest-findings/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/jayelbotvibe-web/hermes-pentest-lab/pentest-findings"><img src="https://agentmods.dev/badge/skills/jayelbotvibe-web/hermes-pentest-lab/pentest-findings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 82 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00047 | $0.07788 |
| Opus 5 | $0.00023 | $0.03894 |
| Sonnet 5 | $0.00009 | $0.01558 |
| Haiku 4.5 | $0.00005 | $0.00779 |
Grade A, and why
pentest-findings 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 11d 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.
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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pentest Finding Encyclopedia
Maps common pentest tool output to finding classification, CVSS 3.1 scoring, severity, and report-ready description/remediation language. Load this skill during the reporting phase of any engagement — it ensures findings are scored consistently and written in professional report language.
How to Use
- Identify the vulnerability class (Web, Network, Auth, Infrastructure, Info Disclosure)
- Jump to the corresponding section
- Match the tool output against "What You See"
- Use the CVSS guidance to score (adjustable per engagement context)
- Use the report language templates — the Description, Impact, and Remediation fields are copy-ready
Web Application
SQL Injection
What You See: sqlmap output: Parameter '#1*' is vulnerable... boolean-based blind or time-based blind or error-based or UNION query
Interpretation: The application constructs SQL queries using unsanitized user input, allowing an attacker to manipulate database queries.
CVSS Scoring:
- Unauthenticated + data extraction possible: CVSS 9.8 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H)
- Authenticated + limited to own data: CVSS 8.8 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H)
- Blind + slow extraction only: CVSS 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N)
- Error-based only (no extraction): CVSS 6.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N)
Severity: Critical (unauthenticated data access), High (authenticated), Medium (error-based only)
CWE: CWE-89 (SQL Injection)
Report — Description:
"SQL injection was identified in the <parameter> parameter of <endpoint>. The application fails to sanitize user-supplied input before incorporating it into database queries. An attacker can manipulate query logic to extract, modify, or delete database contents."
Report — Impact: "Successful exploitation allows an attacker to read arbitrary data from the application database, including user credentials, personal information, and application secrets. In severe cases, the attacker may modify or delete data, or in the case of stacked queries, execute operating system commands on the database server."
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.
- 11d ago First seen · 485 lines · 47 tokens per session scan A 4a209f5cf2d2
pentest-findings is a skill published in the GitHub repository jayelbotvibe-web/hermes-pentest-lab (9 stars, last pushed 17d ago), licensed MIT. It adds 47 tokens to every session and 7,788 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 2026-08-31.
Other skills, from other repositories
hardening-docker-containers-for-production
Hardening Docker containers for production involves applying security best practices aligned with CIS Docker Benchmark v1.8.0 to minimize attack surface, prevent privilege escalation, and enforce leas.
scanning-docker-images-with-trivy
Trivy is a comprehensive open-source vulnerability scanner by Aqua Security that detects vulnerabilities in OS packages, language-specific dependencies, misconfigurations, secrets, and license violati.
securing-container-registry-with-harbor
Harbor is an open-source container registry that provides security features including vulnerability scanning (integrated Trivy), image signing (Notary/Cosign), RBAC, content trust policies, replicatio.
implementing-container-image-minimal-base-with-distroless
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.
performing-docker-bench-security-assessment
Docker Bench for Security is an open-source script that checks dozens of common best practices around deploying Docker containers in production. Based on the CIS Docker Benchmark, it audits host confi.
docker-privesc
Escape Docker containers to host root via 5 techniques.