SKILLEMALL.ai
GitHub ↗ RU Sign in

CC detecting-malicious-npm-packages

Triage npm packages and lockfiles for install-script malware, credential exfiltration, and worming behavior using GuardDog, manual tarball inspection, and dynamic detonation with network/filesystem monitoring. Use when vetting a new dependency, reviewing a package.json/package-lock.json during code review, checking lockfiles against a supply-chain advisory's known-bad versions, or investigating a host suspected of installing a trojanized package.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 5 files · 1 script body ≈ 2 403 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Triage npm packages and lockfiles for install-script malware, credential exfiltration, and worming behavior using GuardDog, manual tarball inspection, and…

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, progress reporting

AnalyzerGitHubDockerAI and agentsPeople and hiringtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
89/100
safety, quality, tests
Safety 60%
95
Quality 40%
81
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Dangerous commands cmd-install-from-url SKILL.md:158
      Installs a package from an untrusted URL / archive (documentation of a security skill)
      npm install ./some-pkg.tgz            # scripts WILL run — sandbox only
      security skill

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 25 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2403 tokens
    • 100Running it twice. Mutating operations check current state

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -42 reference files, but SKILL.md never points to them: the model will not open them
    • +2Single-language instructions
    • +3Description length 450: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 25 items
    • +4Has examples (12 code blocks)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.