MRSFBLOCK
Markdown Review Sidecar Format (MRSF) v1.0 - Sidemark
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](LICENSE) [](MRSF-v1.0.md) [](https://www.npmjs.com/package/@mrsf/cli) [](https://www.npmjs.com/package/@mrsf/mcp) [](https://www.npmjs.com/package/@mrsf/cli) [](https://www.npmjs.com/package/@mrsf/mcp) [](https://marketplace.visualstudio.com/items?itemName=wictor.mrsf-vscode) [](https://marketplace.visualstudio.com/items?itemName=wictor.mrsf-vscode) [](https://pypi.org/project/mrsf/) [](https://www.npmjs.com/package/@mrsf/markdown-it-mrsf) [](https://www.npmjs.com/package/@mrsf/marp-mrsf) [](https://www.npmjs.com/package/@mrsf/marked-mrsf) [](https://www.npmjs.com/package/@mrsf/rehype-mrsf) [
8 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
mrsf_add | write | |
mrsf_add_batch | write | |
mrsf_delete | destructive | |
mrsf_discover | read | |
mrsf_help | read | |
mrsf_list | read | |
mrsf_reanchor | read | |
mrsf_rename | write | |
mrsf_repair | read | |
mrsf_resolve | read | |
mrsf_status | read | |
mrsf_update | write | |
mrsf_validate | read |
Trust audit
BLOCKgrade F · trust 56/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (9 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (24)
const parsed = yaml.load(raw, { schema: yaml.JSON_SCHEMA }) as Record<string, unknown> | null;parsed = yaml.load(trimmed, { schema: yaml.JSON_SCHEMA });parsed = isJson ? JSON.parse(trimmed) : yaml.load(trimmed, { schema: yaml.JSON_SCHEMA });const parsed = yaml.load(trimmed, { schema: yaml.JSON_SCHEMA });.coverage
const filterIcon = showResolved ? "👁" : "👁🗨";
mrsf_delete
.coverage
.vscodeignore
"sidecar_root: ../../etc/reviews\n",
fileURLToPath(new URL("../../../evaluation/reanchor/schema.json", import.meta.url)),"../../../evaluation/reanchor/cases",
"../../../evaluation/reanchor/schema.json",
"../../../evaluation/reanchor/schema.json",
const browser = await chromium.connectOverCDP(`http://127.0.0.1:${process.env.MRSF_TEST_CDP_PORT}`);[ v1.0 - Sidemark
What tools does MRSF expose?
13 in total: 8 read-only, 4 that write, and 1 that can delete or overwrite (mrsf_delete). Every one is listed on this page with its risk.
Is MRSF safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (56/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does MRSF need?
No credential environment variables were found in its source, so it appears to need none.
How does MRSF run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on npm as mrsf-vscode at 0.6.0.
How current is this page?
The grade is for one exact copy of the source (bd28787b8e60), read on 2026-10-09. The repository is watched and re-audited when it changes.