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 msradam/theodosia --skill security-auditgit clone --depth 1 https://github.com/msradam/theodosiaWrote 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/msradam/theodosia/security-audit)<a href="https://agentmods.dev/skills/msradam/theodosia/security-audit"><img src="https://agentmods.dev/badge/skills/msradam/theodosia/security-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/msradam/theodosia/security-audit"><img src="https://agentmods.dev/badge/skills/msradam/theodosia/security-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 | $0.00250 | $0.07714 |
| Opus 5.5 | $0.00100 | $0.03086 |
| Sonnet 5.5 | $0.00050 | $0.01543 |
| Haiku 4.5 | $0.00025 | $0.00771 |
Grade B, and why
security-audit 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 2mo 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.
| AWS IMDSv1 | `http://169.254.169.254/latest/meta-data/iam/security-credentials/` | none (legacy) | 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.
grep -rInE 'urllib\.(request|urlopen)\(|requests\.(get|post)\(.+\+' src/ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -rInE 'child_process\.(exec|execSync)\(|\.spawn\(.+,\s*\{\s*shell' src/ How it starts
The opening of the file, as written. The whole thing — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web App Security Audit
Find the bugs before attackers do. Works equally well for:
- Your own codebase — defensive audit before you get hacked
- A project you have written authorization to audit — GHSA collaborator, bug-bounty scope, CTF engagement
First — what mode are we in?
digraph context {
"Can I read the target's source?" [shape=diamond];
"Do I also have a live URL?" [shape=diamond];
"INSIDE mode" [shape=doublecircle];
"OUTSIDE mode" [shape=doublecircle];
"BOTH mode (ideal)" [shape=doublecircle];
"Can I read the target's source?" -> "Do I also have a live URL?" [label=yes];
"Can I read the target's source?" -> "OUTSIDE mode" [label=no];
"Do I also have a live URL?" -> "BOTH mode (ideal)" [label="yes, running deployment"];
"Do I also have a live URL?" -> "INSIDE mode" [label="no, code only"];
}
Check signals in this order:
| Signal | Mode |
|---|---|
ls shows package.json / Cargo.toml / go.mod / pyproject.toml / Dockerfile / src/ in cwd |
inside (filesystem access to target) |
| User says "my project", "our codebase", "audit this repo", pastes code | inside |
| User gave only a URL / hostname / API endpoint, no filesystem access | outside (black-box) |
| Filesystem access AND a live URL of the same project | both — most powerful |
| Written scope from the maintainer of a project you don't own | outside or both (check cwd) |
Before probing production from outside, you need authorization in writing. Scope artefact (maintainer DM, GHSA collaborator invite, bounty scope). Without it, stop.
INSIDE mode — source-code audit checklist
Read the code before doing anything else. Every bug found here is free (no prod traffic, no scope questions). Work in this order — cheap first:
1. Dependency CVEs and version pins
# Node
npm audit --production # or pnpm audit, yarn audit
grep -E '"(react|next|express|fastify|better-auth|drizzle)":' package.json
# Python
pip-audit || safety check
# Container
grep -E 'FROM\s+.+:latest|FROM\s+.+:\d' Dockerfile* # :latest is a smell
What ships with it
1 file 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.
- 2mo ago First seen · 601 lines · 250 tokens per session scan B 5b5d3e6ae71b
security-audit is a skill published in the GitHub repository msradam/theodosia (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 250 tokens to every session and 7,714 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it B with 3 findings (cloud metadata endpoint, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fastmcp-client-cli
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
systematic-bug-hunting
Use when actually hunting for exploitable bugs at the bench inside an already-authorized engagement — reading a target, running scanners/fuzzers, sitting on a pile of odd-but-inert observations, tempted to report something "probably exploitable", or about to conclude "nothing found". Applies to every target class…
systematic-attacking
Use for ALL authorized offensive-security / bug-bounty work — the single method to find, chain, prove, dedup, and package the highest-value (High/Critical) findings across every domain (web/SaaS, smart-contract/DeFi, infra/cloud, LLM/AI, mobile, binary/firmware). Enforces two iron laws before any offensive action or…
evm-audit-flow
Use when you have a Foundry or Hardhat repository of Solidity or Vyper contracts and want the end-to-end EVM review workflow on native CLIs — a slither static pass, semgrep taint rules, mythril symbolic execution, echidna and medusa invariant fuzzing, halmos formal checks, then a forge build-and-test regression.
vulnhunter-solana
Use when reviewing Solana program code for the account-model bug classes — unchecked account owner, absent signer, discriminator confusion, caller-controlled CPI seeds, PDA-derivation collision, SPL arithmetic overflow, close-and-reinitialize revival, and duplicate-account aliasing — the pattern census that stands in…
persuasive-technical-writing
Use when drafting or revising long-form persuasive technical prose (an essay, post-mortem, launch narrative, or public technical release for X or the web) where the writing must sound human and hold a reader to the end. Do not use for code documentation, changelogs, or short social copy.