backdoor-review SKILL.md skillA
backdoor-review from gsa-tts/agentic-coding-patterns is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gsa-tts/agentic-coding-patterns/backdoor-review@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gsa-tts/agentic-coding-patterns
- Path
.agents/skills/backdoor-review/SKILL.md- Versions recorded
- 3
- Latest version
- v1.0.0, committed Aug 20, 2026
- First version recorded
- Jul 2, 2026
- Size
- 12,860 bytes
- Repository stars
- 16
- License
- CC0-1.0
Read-only adversarial review that flags suspicious-pattern classes (auth bypass, unauthorized persistence, CI tampering, hidden/obfuscated jobs, data exfiltration) using strict Evidence / Hypothesis / Confidence separation — conceptual only, never producing working exploits or intrusion recipes.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill: Backdoor Review Read code, configuration, and CI definitions with an **adversarial eye** and flag **suspicious-pattern classes** that could indicate a backdoor: authentication bypass, unauthorized persistence, CI tampering, hidden or obfuscated jobs, and data-exfiltration channels. Each finding cleanly separates what is **observed** from what is **inferred**, with a stated **confidence**. > **Self-limiting — read this first.** This skill is a **read-only** adversarial > review. It describes suspicious-pattern **classes** and how a human should > **investigate** them. It **NEVER** produces a working exploit, weaponized > proof-of-concept code, or a step-by-step intrusion recipe. Illustrative > snippets are **descriptions of a suspicious shape**, not runnable attacks. > Every finding separates **Evidence** (what is literally present) from > **Hypothesis** (what it might mean) and attaches an explicit **Confidence**. > A finding is a **lead for a human**, not a verdict. When in doubt, flag less > and defer to human review. ## When to Use - Reviewing a PR, dependency update, or fork diff for signs of tampering …
Read the whole file at its exact version.
How to install
mdr add gsa-tts/agentic-coding-patterns/backdoor-review@sha256:d1b7bdb30ea979c6The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_lusxuicby3g7wbgz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 2, 2026 and Aug 20, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-20 | ae5b0dd | 12,860 B | A | view · diff |
| v1.0.0 | 2026-07-28 | ea6ea67 | 12,857 B | A | view · diff |
| v1.0.0 | 2026-07-02 | c736287 | 12,339 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12860 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
gsa-tts/agentic-coding-patterns · 16 stars · license CC0-1.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lusxuicby3g7wbgz GET https://markdownregistry.com/api/v1/resolve?ref=gsa-tts/agentic-coding-patterns/backdoor-review GET https://markdownregistry.com/api/v1/blob/d1b7bdb30ea979c6131b09f71f7ec593cf37102fa71096295570f1f0000e345b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.