fetcher-mcp@0.4.1
CAUTIONPublisher claims: "MCP server for fetching web content using Playwright browser" Observed in sandbox: sends data to cdn.playwright.dev.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-05 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to cdn.playwright.dev.
Behavior trace
Honeypot run · 4 s · 2 scenariost+CategoryObserved action
2.8sfilesystemread ~/.cache/ms-playwright/.links · ~/.cache/ms-playwright/.links/012449f02ce4f07fac91ce0c44bf51274bc3c21b · ~/.cache/ms-playwright outside project
2.8sfilesystemwrote ~/.cache/ms-playwright/.links/012449f02ce4f07fac91ce0c44bf51274bc3c21b
2.8snetworkCONNECT https://cdn.playwright.dev · undeclared
2.8snetworkCONNECT https://cdn.playwright.dev · undeclared
2.8snetworkCONNECT https://cdn.playwright.dev · undeclared
2.8snetworkCONNECT https://cdn.playwright.dev · undeclared
2.8snetworkCONNECT https://cdn.playwright.dev · undeclared
2.8sprocessexec /app/apps/web/node_modules/.bin/playwright
2.8sprocessexec /usr/bin/sed
2.8sprocessexec /usr/bin/dirname
2.8sprocessexec /usr/bin/uname
2.8sprocessexited 1: at process.processTicksAndRejections (node:internal/process/task_queues:89:21)
3.6sprocessdependency install exit 1
3.7sprocessexec /usr/bin/date
3.7sprocessexec /usr/bin/timeout
3.7sclaimedno tools/list reply (exit 0)
3.7sprocessscript backend runs setup only
Static findings
LOW
Context shift attemptREADME.md:255 · Context shift attempt — trying to change operational mode · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01LOW
Context shift attemptREADME.md:257 · Context shift attempt — trying to change operational mode · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
npx invocation of non-well-known packagebuild/tools/browserInstall.js:125 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06LOW
Context shift attemptREADME.md:156 · Context shift attempt — trying to change operational mode · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01LOW
Context shift attemptREADME.md:235 · Context shift attempt — trying to change operational mode · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
npx invocation of non-well-known packagebuild/tools/browserInstall.js:51 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagepackage.json:18 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebuild/tools/browserInstall.js:127 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebuild/tools/browserInstall.js:122 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packagebuild/tools/browserInstall.js:95 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06Cost to the agent
Instructions loaded
≈50 tok
1 file · 22 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0
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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim jaeger: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jaeger