Skills/Glama/dia-mcp

dia-mcp@r1

CAUTION

Publisher claims: "Enables AI agents to control a live Dia browser session over the Chrome DevTools Protocol, including reading pages, clicking, typing, inspecting network and console activity, and taking screenshots without a debug port or restart." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher damnitjoshua · joined 0 days agoInstalls 0Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is dia-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Authorization escalation language; Outbound HTTP to raw IP address. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Outbound HTTP to raw IP addressmcp_server.py:27 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
Authorization escalation languageREADME.md:53 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageAGENTS.md:61 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Outbound HTTP to raw IP addressAGENTS.md:51 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addressextension/background.js:8 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandextension/background.js:283 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using raw IP addressAGENTS.md:67 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressmcp_server.py:27 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedmcp_server.py:119 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.md:53 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Outbound HTTP to raw IP addressAGENTS.md:67 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresstools/selftest.py:16 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressextension/manifest.json:7 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedmcp_server.py:69 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addressextension/background.js:8 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addresstools/selftest.py:16 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Prompt injectionAGENTS.md:61 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
URL using raw IP addressAGENTS.md:51 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagemcp_server.py:1003 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Outbound HTTP to raw IP addressextension/manifest.json:7 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈1,261 tok
2 files · 12 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim damnitjoshua: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. 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 Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim damnitjoshuaPropose a patch to the maintainer