Skills/npm/specguard-mcp

specguard-mcp@0.1.60

VERIFIED

Publisher claims: "MCP server exposing SpecGuard suite intelligence to AI coding agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher yatfa-ai · joined 9 days agoInstalls 4,743Last detonated 54 min ago
$claude mcp add specguard-mcp -- npx -y specguard-mcp
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-05 and scored it 83/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 3 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
2.7sprocessdependency install exit 1
3.0sprocessexec /usr/bin/timeout
3.0sprocessexited 1: Node.js v22.23.4
3.0sclaimedno tools/list reply (exit 1)
3.0sprocessscript backend runs setup only

Static findings

HIGH
Refusal suppressionREADME.md:134 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/src/config.d.ts:97 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/src/tools/lint-intent-annotations.js:161 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/src/support/run-command.js:24 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/support/teardown.js:9 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/support/run-command.js:99 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/support/run-command.js:170 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/support/run-command.js:98 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/support/teardown.d.ts:8 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/support/run-command.js:21 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05