# AI Research Reproduction

> AI Research Reproduction is a community-maintained skill from lllllllama. Anomity scores its risk at 100 out of 100 (critical). It matches 3 dangerous capability combinations.

- **Canonical URL:** https://catalog.anomity.ai/skill/ai-research-reproduction
- **Kind:** Skill
- **Publisher:** lllllllama
- **Trust level:** community
- **Risk score:** 100/100 (critical)
- **Website:** https://github.com/lllllllama
- **Last updated:** 2026-09-02
- **JSON:** https://catalog.anomity.ai/api/entries/skill/ai-research-reproduction

## Description

Orchestrates end-to-end reproduction of a deep-learning repository — reading the README, setting up the environment, running training or evaluation, and tracking evidence of what actually ran.

Capabilities are filesystem read and write, shell execution, and outbound network: the full-control combination, and correctly so. Reproducing research means executing code from a repository you did not write, with dependencies you did not audit, which is one of the most direct paths from "an agent read something" to "arbitrary code ran on this machine". Container it.

## Why it scored 100

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Established community project | -10 | trust offset |  |
| 2 high-risk capabilities: filesystem:write, shell:execute | +20 | critical |  |
| Data exfiltration risk (high) | +15 | high | Shell execution combined with outbound network access can exfiltrate arbitrary data from the machine. |
| Persistence + execution risk (medium) | +5 | medium | Shell execution plus filesystem write means the agent can plant persistent backdoors (e.g. modifying startup scripts). |
| Full-control risk (critical) | +25 | critical | Shell + filesystem write + network is effectively a remote shell on the employee machine. |

Clamped result: **100/100**, band **critical**.

## Capabilities

| Capability | Name | Security implication |
| --- | --- | --- |
| `filesystem:read` | Filesystem read | Can read files on the host system. Used for context, indexing, or analysis. |
| `filesystem:write` | Filesystem write | Can create, edit, or delete files on the host system. High-impact capability — anything from helpful edits to planting persistence. |
| `shell:execute` | Shell execution | Can run arbitrary shell commands. Combined with network access this becomes effectively a remote shell. |
| `network:outbound` | Outbound network | Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access. |

## Dangerous combinations matched

### Data exfiltration risk (high)

Shell execution combined with outbound network access can exfiltrate arbitrary data from the machine.

Capabilities: `shell:execute`, `network:outbound`

### Persistence + execution risk (medium)

Shell execution plus filesystem write means the agent can plant persistent backdoors (e.g. modifying startup scripts).

Capabilities: `shell:execute`, `filesystem:write`

### Full-control risk (critical)

Shell + filesystem write + network is effectively a remote shell on the employee machine.

Capabilities: `shell:execute`, `filesystem:write`, `network:outbound`

## Related skills

- [Using Git Worktrees](https://catalog.anomity.ai/skill/using-git-worktrees) — risk 65 (high)
- [Browser Act](https://catalog.anomity.ai/skill/browser-act) — risk 95 (critical)
- [Best Practices](https://catalog.anomity.ai/skill/web-best-practices) — risk 50 (medium)
- [Check](https://catalog.anomity.ai/skill/check-review) — risk 50 (medium)
- [Test-Driven Development](https://catalog.anomity.ai/skill/test-driven-development) — risk 50 (medium)
- [Writing Skills](https://catalog.anomity.ai/skill/writing-skills) — risk 50 (medium)

---

Source: Anomity Catalog (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json