skim-mcp@0.1.1
CAUTION· not startedPublisher claims: "Token-efficient skim-then-expand I/O for agentic models (Claude Code / desktop Claude) via MCP" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Image alt text carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
print(f"\nNext: npx -y repomix \"{os.path.abspath(corpus_dir)}\" --compress --style plain "Fix: Pin versions and sources; vendor anything fetched at install time.skim live token-savings dashboard: 76.5% saved overall, 261,826 tokens in, 61,452 out, a By-session table (docs-pass 79.4%, api-refactor 74.7%) with last-activeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.out = subprocess.run([sys.executable, "-m", "pytest", "--collect-only", "-q"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kwargs["start_new_session"] = True # own process group, so timeout can kill the whole treeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.What did you run, what did you expect, what did you get instead?Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.help="where to write the prefer-skim rule (default: ./CLAUDE.md)")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.("import os\n", ".py"), # leading BOMFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.description="Register skim with Claude Code and write the CLAUDE.md preference rule "Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.return subprocess.run(attempt, timeout=60).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.skim-mcp install --rule global # write the rule to ~/.claude/CLAUDE.md insteadFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx -y repomix <corpus_dir> --compress --style plain --output <corpus_dir>/repomix_out.txtFix: Pin versions and sources; vendor anything fetched at install time.proc = subprocess.Popen(command, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.skim-mcp install --rule global # write the rule to ~/.claude/CLAUDE.md insteadFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**2. Make it automatic — add a rule to your `CLAUDE.md`** (a project one, or global `~/.claude/CLAUDE.md`)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**2. Make it automatic — add a rule to your `CLAUDE.md`** (a project one, or global `~/.claude/CLAUDE.md`)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.return subprocess.run(["cmd", "/c", *attempt], timeout=60).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["taskkill", "/F", "/T", "/PID", str(proc.pid)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.skim-mcp install --rule global # write the rule to ~/.claude/CLAUDE.md insteadFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for skim-mcp@0.1.1 as of 38 min ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim helloderekg: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Hidden zero-width characters detected≈ +2 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.