Skills/npm/socratic-method

socratic-method@0.4.0

VERIFIED· install only

Publisher claims: "An Agent Skill that makes an AI coding agent cross-examine its own work before it ships: predict-then-run, gated, and mostly silent. One npx command installs it for every tool that reads the Agent Skills format - Claude Code, Codex, Cursor, VS Code, Gemin" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ergini · publishing for 130 daysInstalls 64Last detonated 56 min ago
$claude mcp add socratic-method -- npx -y socratic-method
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.3.2

vet-skills diff socratic-method 0.3.2 0.4.0

In the sandbox, this version reached for nothing 0.3.2 did not. Compared from the two recorded runs, not from source.

0.3.2 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocess1 of 1 bundled script run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagebin/install.js:146 · npx invocation of non-well-known package — may execute untrusted codenpx socratic-method [options]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:161 · npx invocation of non-well-known package — may execute untrusted codenpx socratic-method # every tool, this projectFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:23 · npx invocation of non-well-known package — may execute untrusted code// makes the bare `npx socratic-method` work everywhere instead of in one tool.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:163 · npx invocation of non-well-known package — may execute untrusted codenpx socratic-method --tool cursor # ./.cursor/skillsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackage.json:4 · npx invocation of non-well-known package — may execute untrusted code…e its own work before it ships: predict-then-run, gated, and mostly silent. One npx command installs it for every tool that reads the Agent Skills format - Claude Code, Co…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:162 · npx invocation of non-well-known package — may execute untrusted codenpx socratic-method --global # every tool, every projectFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈5,043 tok
1 file · 9 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for socratic-method@0.4.0 as of 21 min ago. This is the package itself, not its dependencies.