Skills/PyPI/peek-mcp

peek-mcp@0.5.17

VERIFIED· not started

Publisher claims: "Let AI agents see your UI — point at elements, annotate, and get instant visual context for AI-powered code editing." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher zly1203 · publishing for 241 daysInstalls 145Last detonated 1 h ago
$claude mcp add peek-mcp -- uvx peek-mcp
WatchReport an issue

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: Verified 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 codeAlso evil.com — not the publisher's domain; check what for before connecting.
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.

$vet-skills run --net declared -- uvx peek-mcp

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 2026-11-14 and scored it 85/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedsrc/cli.py:67 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/cli.py:127 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/cli.py:88 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandstatic/inspector.js:928 · Process kill command — agent can terminate processes// would kill our own button click handlers before they run.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/cli.py:132 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hex-encoded URLtests/test_security.py:78 · Hex-encoded URL — attempt to bypass URL filtering"http://0x7f000001:8080", # hex IP for 127.0.0.1 (SSRF bypass)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:189 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileEither your dev server isn't running, or the agent guessed the wrong port. Add the `CLAUDE.md` snippet above so the agent knows your real port; start your dev server before asking for a screenshot.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
URL to a private-network addresstests/test_security.py:106 · URL to a private-network address — a LAN or development target"http://10.0.0.1:8080", # LAN IPFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
AWS access key pattern detectedtests/test_redact.py:31 · AWS access key pattern detected — possible hardcoded or harvested keyassert "AKIAIOSFODNN7EXAMPLE" not in outFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
LOW
URL to a private-network addresstests/test_screenshot.py:188 · URL to a private-network address — a LAN or development targetassert validate_url("http://192.168.1.5:3000") == "http://192.168.1.5:3000"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
AWS access key pattern detectedtests/test_redact.py:29 · AWS access key pattern detected — possible hardcoded or harvested keytext = "Found AWS key AKIAIOSFODNN7EXAMPLE in env"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
LOW
HTML comment carrying imperative instructions to the agenttests/e2e/fixtures/lazy_images.html:34 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileEach <img> uses loading="lazy" pointing at a tiny inline-data SVG that NEVER fires `load` until the browser decides to fetch it (i.e. when the user scrolls closFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/cli.py:210 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileprint(" Recommended: add this to your project's CLAUDE.md so the agent")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
URL using a raw public IP addresstests/test_screenshot.py:165 · URL using a raw public IP address — may bypass domain-based filteringvalidate_url("http://8.8.8.8")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
GitHub token pattern detectedtests/test_redact.py:22 · GitHub token pattern detected — possible hardcoded or harvested tokentext = "Auth: ghp_abcdefghijklmnopqrstuvwxyz1234567890ABC"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
URL with embedded credentialstests/e2e/fixtures/webfont_page.html:15 · URL with embedded credentials — may be phishing or credential leaking<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600&family=Newsreader:ital,wght@0,400;1,400&display=swap" rel="stylesheet">Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
GitHub token pattern detectedtests/test_redact.py:135 · GitHub token pattern detected — possible hardcoded or harvested token"outerHTML": '<div>Token: ghp_realgithubtoken1234567890abcdefghij1234567890</div>',Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
LOW
URL to a private-network addresstests/test_security.py:105 · URL to a private-network address — a LAN or development target"http://192.168.1.5:3000", # LAN IPFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL to the cloud instance metadata addresstests/test_screenshot.py:167 · URL to the cloud instance metadata address — reads the VM's credentialsvalidate_url("http://169.254.169.254/latest/meta-data/")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
LOW
URL to a private-network addresstests/test_screenshot.py:189 · URL to a private-network address — a LAN or development targetassert validate_url("http://10.0.0.1:8080") == "http://10.0.0.1:8080"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_security.py:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresp = client.get("/captures//etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addresstests/test_security.py:107 · URL to a private-network address — a LAN or development target"http://172.16.0.1:3000", # LAN IPFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Hex-encoded string detectedtests/e2e/test_bridge.py:19 · Hex-encoded string detected — may contain obfuscated payloadsb"\x00\x00\x00\x01\x08\x02\x00\x00\x00\x90wS\xde\x00"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionstatic/modern-screenshot.js:7 · File type combined with upload action — agent may exfiltrate local data files…r(),e.defaultComputedStyles.clear(),e.sandbox){try{e.sandbox.remove()}catch(t){e.log.warn("Failed to destroyContext",t)}e.sandbox=void 0}e.workers=[],e.fontFamilies.clear(),e.fontCssTexts.clear(),e.requests.clear(),e.tasks=[],e.shadowRoots…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstests/test_security.py:42 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""GET /captures//etc/passwd should not serve system files."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Hex-encoded string detectedtests/conftest.py:47 · Hex-encoded string detected — may contain obfuscated payloadsb"\x00\x00\x00\x01\x08\x02\x00\x00\x00\x90wS\xde\x00"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:86 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd this to your project's `CLAUDE.md` (or `.cursorrules`, etc.):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Hex-encoded string detectedtests/conftest.py:48 · Hex-encoded string detected — may contain obfuscated payloadsb"\x00\x00\x0cIDATx\x9cc\xf8\x0f\x00\x00\x01\x01\x00"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionstatic/modern-screenshot.js:6 · File type combined with upload action — agent may exfiltrate local data files…ageInterval:a}=t;r.time("image to canvas");const s=yield L(e,{timeout:n,onWarn:t.log.warn}),{canvas:o,context2d:c}=bt(e.ownerDocument,t),u=()=>{try{c==null||c.drawImage(s,0,0,o.width,o.height)}catch(l){t.log.warn("Failed to drawImage",l)}}…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Hex-encoded string detectedtests/e2e/test_bridge.py:20 · Hex-encoded string detected — may contain obfuscated payloadsb"\x00\x00\x0cIDATx\x9cc\xf8\x0f\x00\x00\x01\x01\x00"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
URL to the cloud instance metadata addresstests/test_security.py:80 · URL to the cloud instance metadata address — reads the VM's credentials"http://169.254.169.254", # AWS metadata (link-local)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Hex-encoded URLtests/test_screenshot.py:174 · Hex-encoded URL — attempt to bypass URL filteringvalidate_url("http://0x7f000001:8080")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
HTTP URL with a raw public IP addresstests/test_screenshot.py:165 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot namevalidate_url("http://8.8.8.8")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:104 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd this to your project's `CLAUDE.md` (or `.cursorrules`, etc.):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/test_screenshot.py:205 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvalidate_url("file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:207 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileEither your dev server isn't running, or the agent guessed the wrong port. Add the `CLAUDE.md` snippet above so the agent knows your real port; start your dev server before asking for a screenshot.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈64 tok
1 file · 39 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

No advisories in OSV for peek-mcp@0.5.17 as of 47 min ago. This is the package itself, not its dependencies.