Cynical SallyBLOCK
Brutally honest senior-engineer code reviews for Claude Code, Cursor & Windsurf - and your terminal. Scores, evidence-backed issues, usable fixes.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Cynical Sally
Brutally honest code reviews. In your terminal and your AI editor. Because "You're absolutely right" is probably absolutely wrong. npm i -g @cynicalsally/cli · MCP server for Claude Code, Cursor & Windsurf
784cd3af253aOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add cli -- npx -y @cynicalsally/[email protected] mcp
Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
sally_brainstorm | read | |
sally_explain | read | |
sally_frontend | read | |
sally_marketing | read | |
sally_refactor | read | |
sally_review_pr | read | |
sally_roast | read | |
sally_usage | read |
Trust audit
BLOCKgrade F · trust 59/100 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 | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (8 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (15)
exec(`${openCmd} "${url}"`);exec(`osascript -e 'display notification "${safeMessage}" with title "${safeTitle}"'`);exec(`notify-send "${safeTitle}" "${safeMessage}"`);"id_rsa",
"id_ecdsa",
"id_ed25519",
".netrc",
const { version } = require("../../package.json") as { version: string };@modelcontextprotocol/sdk, chalk, commander, inquirer, ora, @types/node, typescript
assets/banner.png
assets/full-suite.png
assets/tool-brainstorm.png
assets/tool-explain.png
assets/tool-frontend.png
│ 1. Collect files │ Secret files (.env, keys, certs, credential
Gates applied: no_behavioural_pass.
784cd3af253afull audit observations/trust-audit/mcp-server/w1ckedxt__cynical-sally.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 784cd3af253a | BLOCK | F | 59 | first audit |
Questions
What is the Cynical Sally MCP server?
Brutally honest senior-engineer code reviews for Claude Code, Cursor & Windsurf - and your terminal. Scores, evidence-backed issues, usable fixes.
What tools does Cynical Sally expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Cynical Sally safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (59/100) and found 7 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Cynical Sally need?
No credential environment variables were found in its source, so it appears to need none.
How does Cynical Sally run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @cynicalsally/cli at 0.7.0.
How current is this page?
The grade is for one exact copy of the source (784cd3af253a), read on 2026-10-07. The repository is watched and re-audited when it changes.