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-remediatorgit 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-remediator)<a href="https://agentmods.dev/skills/eresussecurity/appsec-skills/eresus-remediator"><img src="https://agentmods.dev/badge/skills/eresussecurity/appsec-skills/eresus-remediator/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-remediator"><img src="https://agentmods.dev/badge/skills/eresussecurity/appsec-skills/eresus-remediator.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 | $0.00084 | $0.01027 |
| Opus 5 | $0.00042 | $0.00513 |
| Sonnet 5 | $0.00017 | $0.00205 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
eresus-remediator 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 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.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAST Remediation
Purpose
Turn confirmed or likely security findings into safe, minimal, production-ready code changes. Prefer root-cause fixes over cosmetic mitigations, preserve legitimate behavior, and reduce the chance of regressions or bypasses.
Inputs
This skill works best when at least one of the following is available:
- a finding from
eresus-sast-scanner - a security review comment or PR thread
- a vulnerable file/function/endpoint
- a proof-of-concept payload or attack path
If eresus-sast-scanner is installed, load the matching vulnerability knowledge file(s) from its
references/ directory before patching.
Workflow
Step 1: Reconstruct the Vulnerability Path
Before editing code, confirm:
- the attacker-controlled source
- the transformation path
- the vulnerable sink
- the intended business behavior that must still work after the fix
Do not patch from the label alone. Patch the actual code path.
Step 2: Choose the Right Fix Layer
Prefer the highest-leverage fix that closes the whole class of issue:
| Problem Type | Preferred Fix |
|---|---|
| SQL / NoSQL injection | Parameterization, safe query builders, strict allowlists |
| XSS | Context-specific output encoding or safe templating APIs |
| SSRF | Destination allowlists, URL parser validation, egress restrictions |
| Path traversal | Canonicalization plus base-directory enforcement |
| Auth / IDOR | Server-side authorization at object/action boundary |
| CSRF | Framework-native CSRF defense, same-site cookies, token checks |
| File upload | Type/content validation, non-webroot storage, random filenames |
| Serialization / deserialization | Explicit DTOs, allowlisted types, safe parser settings, integrity checks |
| Weak crypto | Modern primitives, strong secrets, secure randomness |
| Race conditions | Atomic operations, locking, compare-and-set, transaction boundaries |
Fix at the sink when possible, but move the fix earlier if many sinks share the same unsafe input path.
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 · 141 lines · 84 tokens per session scan A e9ee01b95775
eresus-remediator is a skill published in the GitHub repository EresusSecurity/appsec-skills (7 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,027 once invoked, about $0.0004 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
ai-skill-auditor
A universal, dependency-free Node.js tool to statically audit AI Skills and local agents for malicious patterns.
smart-contract-audit
Comprehensive smart contract security audit framework with multi-expert analysis. Use for full audits of Ethereum / EVM Solidity and Vyper, Solana / SVM Anchor Rust, TON / FunC / Tact, or Sui / Move projects.
infrastructure-audit
Comprehensive infrastructure security audit framework for IaC, Docker, Kubernetes, and cloud configurations. Use for full infrastructure audits.
broken-access-control
Replay captured requests with swapped identities and bumped object IDs to surface broken access control. Use when testing for IDOR or authz flaws.
jwt-attacks
Forge and re-sign captured JWTs to test signature validation - algorithm confusion (alg:none, RS256 to HS256), key injection, and secret cracking. Use when testing JWT or bearer-token auth.
ssrf-oob
Prove blind SSRF by injecting an out-of-band callback into URL params and forwarding headers, then watching for the hit. Use when testing for SSRF.