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 cyborg-garden/hermes-agent-mt --skill web-pentestgit clone --depth 1 https://github.com/cyborg-garden/hermes-agent-mtWrote 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/cyborg-garden/hermes-agent-mt/web-pentest)<a href="https://agentmods.dev/skills/cyborg-garden/hermes-agent-mt/web-pentest"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/web-pentest/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/cyborg-garden/hermes-agent-mt/web-pentest"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/web-pentest.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 | $0.00070 | $0.03239 |
| Opus 5 | $0.00035 | $0.01620 |
| Sonnet 5 | $0.00014 | $0.00648 |
| Haiku 4.5 | $0.00007 | $0.00324 |
Grade B, and why
web-pentest scanned grade B with 3 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 6d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
4. **Cloud metadata is off by default.** Do not probe `169.254.169.254`, 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.
active scanning. Reading public pages with `curl` is fine; sending Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
2. **Inventory sinks** — every `execute(`, `os.system(`, `eval(`, This is a copy
91% identical to web-pentest — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Application Penetration Testing
A phased pentesting workflow for running web applications. Adapted from Shannon's pipeline (Keygraph, AGPL — concepts only, no code borrowed). Built around three rules:
- No exploit, no report — every finding requires reproducible evidence.
- Bounded scope — every active request goes against a target the operator pre-declared. Off-scope hosts are refused.
- Bypass exhaustion before false-positive dismissal — a "blocked" payload is not a clean bill of health until you've tried the bypass set.
⚠️ Hard Guardrails — Read Before Every Engagement
Violating any of these invalidates the engagement and may be illegal.
-
Authorization gate. Before the first active scan in a session, you MUST confirm with the user, in writing, that they own or have written authorization to test the target. Record the acknowledgement in
engagement/authorization.md(see template). No acknowledgement → no active scanning. Reading public pages withcurlis fine; sending payloads is not. -
Scope allowlist. Maintain
engagement/scope.txt— one hostname or CIDR per line. Everynmap,curl,whatweb, browser navigation, or payload-bearing request MUST be against an entry in scope. If a target redirects you off-scope (3xx to a different host, a link in HTML), STOP and confirm with the user before following. -
No production systems without paper. If the user hasn't told you "yes, prod is in scope and I have written sign-off," assume not. Default targets are staging, local docker, dedicated test instances.
-
Cloud metadata is off by default. Do not probe
169.254.169.254,metadata.google.internal,100.100.100.200,[fd00:ec2::254], or equivalent unless the engagement explicitly includes SSRF-to-metadata as a goal AND the target is one you control. The agent's browser tool can reach these from inside your own infrastructure — don't. -
Destructive payloads need approval. SQLi payloads that DROP/DELETE, filesystem-write SSTI, command injection with
rm/shutdown/mkfs, anything that mutates beyond a single test row → ASK FIRST. Theapproval.pysystem catches some; don't rely on it alone.
What ships with it
8 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.
- references/bypass-techniques.md 4.5 KB
- references/exploitation-techniques.md 6.7 KB
- references/scope-enforcement.md 4.0 KB
- references/vuln-taxonomy.md 4.3 KB
- scripts/recon-scan.sh 3.8 KB runs code
- templates/authorization.md 2.4 KB
- templates/exploitation-queue.json 1.2 KB
- templates/pentest-report.md 4.6 KB
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.
- 6d ago First seen · 334 lines · 70 tokens per session scan B 435f1a9c868a
web-pentest is a skill published in the GitHub repository cyborg-garden/hermes-agent-mt (13 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 3,239 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (cloud metadata endpoint, makes network calls, runs shell commands). It is 91% identical to web-pentest, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
booth-purchase-automation
Buy a real BOOTH item: search, add to cart, confirm, pay, download via browser CDP.
vrchat-assistant-development
Use when developing new features or fixing bugs in the vrchat-assistant repo: add an MCP tool, modify existing behavior, or submit a PR. Loads the authoritative DEVELOPMENT.md before any code change.