Skills/PyPI/rtings-mcp

rtings-mcp@0.3.6

BLOCKED

Publisher claims: "MCP server exposing RTINGS.com test data as structured tools" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher averyy · joined 5 days agoInstalls 838Last detonated 8 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-03 and scored it 45/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent; document.cookie access. 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
0.2sprocessdependency install exit 1
0.3sprocessexec /usr/bin/timeout
0.3sprocessexec .venv/bin/rtings-mcp
0.3sprocessexited 127: timeout: failed to run command '.venv/bin/rtings-mcp': No such file or directory
0.3sclaimedno tools/list reply (exit 127)
0.3sprocessscript backend runs setup only

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentgibbys-avs.html:1005 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentgibbys-avs.html:6087 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
document.cookie accessgibbys-avs.html:400 · document.cookie access — can steal session cookiesFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
HTML comment carrying imperative instructions to the agentgibbys-avs.html:210 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
document.cookie accessgibbys-avs.html:375 · document.cookie access — can steal session cookiesFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Refusal suppressionSPEC.md:880 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/rtings_mcp/browser_auth.py:27 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/rtings_mcp/browser_auth.py:101 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_browser_auth.py:1 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
URL with embedded credentialsgibbys-avs.html:37 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedsrc/rtings_mcp/browser_auth.py:217 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
document.cookie accesssrc/rtings_mcp/browser_auth.py:9 · document.cookie access — can steal session cookiesFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandtests/test_browser_auth.py:3 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
document.cookie accesssrc/rtings_mcp/cli.py:142 · document.cookie access — can steal session cookiesFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Base64 encoding combined with network callgibbys-avs.html:563 · Base64 encoding combined with network call — potential data exfiltrationFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Process kill commandsrc/rtings_mcp/browser_auth.py:186 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/rtings_mcp/browser_auth.py:181 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
document.cookie accesssrc/rtings_mcp/auth.py:186 · document.cookie access — can steal session cookiesFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
document.cookie accessgibbys-avs.html:403 · document.cookie access — can steal session cookiesFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandtests/test_browser_auth.py:77 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

What would make this Verified

35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
  3. Unclaimed publisher≈ +8 on the totalClaim averyy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  6. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim averyy