Skills/npm/dsh-nerd-mode

dsh-nerd-mode@0.5.2

VERIFIED· install only

Publisher claims: "A study switch and study skills for DeepSeek Harness." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher bocchii-the-code · publishing for 18 daysInstalls 2,018Last detonated 27 min ago
$claude mcp add dsh-nerd-mode -- npx -y dsh-nerd-mode
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 88/100 (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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageskills/humanizer/.github/workflows/validate.yml:25 · npx invocation of non-well-known package — may execute untrusted coderun: npx --yes [email protected] add . --listFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandlib/index.js:468 · Process kill command — agent can terminate processes// shortcut: the kill reaches cmd.exe only, upgrade to a tree kill ifFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageskills/convert-documents-to-markdown/SKILL.md:14 · npx invocation of non-well-known package — may execute untrusted codenpx -y @firecrawl/anydoc <file> # Markdown to stdoutFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/humanizer/AGENTS.md:32 · npx invocation of non-well-known package — may execute untrusted code- **Checks:** Before publishing, run `python3 scripts/validate-package.py`, `npx skills add . --list`, and `claude plugin validate .`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/convert-documents-to-markdown/SKILL.md:15 · npx invocation of non-well-known package — may execute untrusted codenpx -y @firecrawl/anydoc <file> -o out.md # write to a fileFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/convert-documents-to-markdown/SKILL.md:16 · npx invocation of non-well-known package — may execute untrusted codenpx -y @firecrawl/anydoc - --format csv < f # read stdinFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈27,217 tok
8 files · 39 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 dsh-nerd-mode@0.5.2 as of 3 min ago. This is the package itself, not its dependencies.