aegis-llm-ai is agent-read markdown (skill) from as-foss/aegis-skills: 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..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
mdr add as-foss/aegis-skills/aegis-llm-ai@git:20260826.9702747mdr add as-foss/aegis-skills/aegis-llm-ai@sha256:a4a8739113fd2695Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_itqueut6t2zm52kr)
0 badge views in 30 days
| 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 |
as-foss/aegis-skills · 12 stars · license Apache-2.0 · pushed 2026-08-26 · branch master
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