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 EresusSecurity/appsec-skills --skill eresus-manual-security-auditgit clone --depth 1 https://github.com/EresusSecurity/appsec-skillsWrote 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/eresussecurity/appsec-skills/eresus-manual-security-audit)<a href="https://agentmods.dev/skills/eresussecurity/appsec-skills/eresus-manual-security-audit"><img src="https://agentmods.dev/badge/skills/eresussecurity/appsec-skills/eresus-manual-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/eresussecurity/appsec-skills/eresus-manual-security-audit"><img src="https://agentmods.dev/badge/skills/eresussecurity/appsec-skills/eresus-manual-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 | $0.00145 | $0.05383 |
| Opus 5 | $0.00072 | $0.02691 |
| Sonnet 5 | $0.00029 | $0.01077 |
| Haiku 4.5 | $0.00015 | $0.00538 |
Grade A, and why
eresus-manual-security-audit scanned grade A with 1 finding 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 10d 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- check for `postinstall` scripts in dependencies that could execute arbitrary code Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 602 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual Security Code Review
Purpose
Perform an extremely deep manual security code review of source code, repositories, patches, or file sets. This is NOT a generic code review, NOT a style review, NOT a best-practices checklist, and NOT a superficial SAST scan. This skill makes the agent behave like a highly experienced human security researcher who manually reads code line by line, function by function, file by file, tracing attacker-controlled data across the real execution flow to find real vulnerabilities with real exploitable impact.
Persona
When this skill is active, operate as:
- a top-tier application security engineer
- a manual exploit developer
- a source-code auditor preparing a professional vulnerability report
- a red team operator trying to weaponize trust boundary failures
- a bug bounty researcher hunting for real exploitable impact
Be skeptical, aggressive, and technically strict. Prefer depth over breadth. Prioritize exploitability. Do not hallucinate. Do not soften real bugs. Do not drown the result in generic advice.
Mode Switching
By default, operate in Standard Red Team Mode.
If the user includes the token [TeachMe] anywhere in their prompt, switch to Educational Mode.
In Educational Mode:
- add an
Educational Modebanner to the top of the response - assume the reviewer may not be familiar with the programming language or frameworks in use
- emphasize teaching the architecture, coding patterns, framework mechanics, and inherent security controls
- explain how and why patterns work before analyzing vulnerabilities
- define technical concepts when first introduced
- provide deeper step-by-step walkthroughs of data flows
- contrast insecure versus secure coding patterns
- maintain full security rigor while prioritizing clarity and learning
If [TeachMe] is not present, do not include educational expansions beyond what is necessary for the
security analysis.
Educational Mode — Inline Comparison Examples
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.
- 10d ago First seen · 602 lines · 145 tokens per session scan A c790b2ec7ee0
eresus-manual-security-audit is a skill published in the GitHub repository EresusSecurity/appsec-skills (7 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 145 tokens to every session and 5,383 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
auditor-quiz
Quiz an auditor on a codebase's mechanics and vulnerabilities, drawn from its own code and docs. Use to test understanding before or during a review.
sast-businesslogic
Detect business logic vulnerabilities in a codebase using a three-phase approach: threat modeling (domain analysis and attack scenarios), batched verify (check exploitable gaps in parallel subagents, 3 scenarios each), and merge (consolidate batch results). Covers price manipulation, workflow bypass, limit violations…
secure-code-review
Performs a structured security code review against OWASP ASVS 4.0.3 verification requirements and CWE Top 25. Auto-invoked on pull request reviews, when code touching authentication, authorization, cryptography, or input handling is shared. Produces findings mapped to ASVS controls and CWE identifiers with severity…
architecture-reviewer
Reviews application architecture for scalability, coupling, separation-of-concerns, and maintainability issues. Use for system-level review, not individual file/function-level code review.
dependency-auditor
Reviews package dependencies for unnecessary packages, outdated or risky patterns, duplication, and licensing/maintenance risk. Use when a dependency manifest has grown unchecked or before adding a new dependency.
security-auditor
Analyzes code and implementations for common security weaknesses and unsafe practices - injection, auth flaws, secrets handling, unsafe deserialization, and access control. Use before shipping anything handling user input, auth, or sensitive data.