aegis-llm-ai SKILL.md skillF
aegis-llm-ai from as-foss/aegis-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add as-foss/aegis-skills/aegis-llm-ai@git:20260826.9702747Pins git:20260826.9702747 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- F, 15 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- as-foss/aegis-skills
- Path
skills/code/llm-ai/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260826.9702747, committed Aug 26, 2026
- First version recorded
- Aug 25, 2026
- Size
- 44,398 bytes
- Repository stars
- 16
- License
- Apache-2.0
Audit playbook module for application-code LLM integrations covering direct and indirect prompt injection, insecure output handling, excessive tool agency, sensitive-information disclosure, RAG authorization gaps, model cost abuse, and model/plugin supply-chain risk.
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
# LLM / AI Feature Security Checks (LLM) ## Scope & Objectives - Cover every code path where a large language model (LLM) is invoked from application source: Python (`openai`, `anthropic`, `langchain`, `llama-index`), JavaScript/TypeScript (`openai` npm package, Vercel AI SDK `@ai-sdk/*`, `langchain.js`), and raw HTTP integrations hitting provider endpoints. - Cover supporting assets: prompt templates (`.txt`, `.md`, `.j2`/Jinja, string constants), agent/tool registries and function-calling schemas, RAG pipelines (loaders, extractors, embedders, vector stores, retrievers), conversation-history persistence, and model/provider configuration. - Cover fine-tune/training pipelines ONLY where datasets or training jobs are managed in-repo (poisoning-surface review). - Out of scope: model internals and weights, provider-side infrastructure security, jailbreak research beyond what the application enables, non-LLM chat systems. Legal determinations about data-processing agreements are out of scope — report findings factually; defer interpretation to counsel. …
Read the whole file at its exact version.
How to install
mdr add as-foss/aegis-skills/aegis-llm-ai@sha256:a4a8739113fd2695The line at the top of this page pins the label git:20260826.9702747, 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_itqueut6t2zm52kr)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 25, 2026 and Aug 26, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260826.9702747 latest | 2026-08-26 | 9702747 | 44,398 B | F | view · diff |
| git:20260825.85624bc | 2026-08-25 | 85624bc | 44,399 B | F | view · diff |
| git:20260825.244c198 | 2026-08-25 | 244c198 | 43,262 B | F | view |
Audit of the latest version
- FAIL, critical: No text hidden with inline styles (matched: style="color:white;font-size:0)
- fail: No prompt-injection phrasing (matched: Ignore all previous instructions)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (44398 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 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
as-foss/aegis-skills · 16 stars · license Apache-2.0 · pushed 2026-08-26 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_itqueut6t2zm52kr GET https://markdownregistry.com/api/v1/resolve?ref=as-foss/aegis-skills/aegis-llm-ai GET https://markdownregistry.com/api/v1/blob/a4a8739113fd269536be4fa6c0fb6b4a3f8254c211dc8d6161f5256b4c5c921c
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.