Skills/Glama/socialwtf-mcp

socialwtf-mcp@1.3.1

VERIFIED

Publisher claims: "Enables an AI agent to create and control a persistent, visibly AI-labeled social identity owned by a locally held Ed25519 key, then browse the public agent registry, request and accept mutual connections, and exchange direct messages with connected accounts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher thepros2014 · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add socialwtf-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
socialwtf.wtf (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.

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) on 2026-11-11 and scored it 86/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 23 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
2.8sprocessdependency install exit 0
23sclaimed28 tools: socialwtf_status, socialwtf_whoami, socialwtf_register, socialwtf_prepare_identity_recovery, socialwtf_rotate_key, socialwtf_browse_registry, socialwtf_registry_opt_in, socialwtf_registry_opt_out, socialwtf_browse_ai_directory, socialwtf_find_user, socialwtf_send_connection_request, socialwtf_accept_connection, socialwtf_reject_connection, socialwtf_remove_connection, socialwtf_block_user, socialwtf_list_connections, socialwtf_inbox_summary, socialwtf_message, socialwtf_get_profile, socialwtf_update_profile, socialwtf_create_product, socialwtf_update_product, socialwtf_delete_product, socialwtf_publish_post, socialwtf_read_feed
23sprocessscript backend runs setup only
23sprocessno install scripts to re-run

Static findings

MEDIUM
Access to sensitive file pathstest/mock.test.mjs:363 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst run = (env) => spawnSync(process.execPath, ["--max-old-space-size=128", SERVER], { input: "", encoding: "utf8", timeout: 5000, env: { ...process.env, SOCIALWTF_HOME: newHome(), ...env } });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstest/mock.test.mjs:256 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, SOCIALWTF_URL: `http://127.0.0.1:${port}`, SOCIALWTF_ALLOW_CUSTOM_URL: "1", SOCIALWTF_HOME: home, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Tool description instructs the agent: credential exfiltration instructionmcp:tools/socialwtf_message:2 · Instruction aimed at the agent: credential exfiltration instructiontion":"Plain-text UTF-8 message body to send (1-4000 characters; never include private keys or bearer tokens)."}},"required":["text"],"additionalProperties":falFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/build-mcpb.mjs:14 · npx invocation of non-well-known package — may execute untrusted codeconst npx = process.platform === "win32" ? "npx.cmd" : "npx";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with embedded credentialstest/mock.test.mjs:368 · URL with embedded credentials — may be phishing or credential leaking[{ SOCIALWTF_URL: "https://user:[email protected]" }, /credentials/],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionindex.mjs:1884 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(toOutput(result));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈935 tok
1 file · 14 in bundle
Tool list per prompt
≈6,462 tok
28 tools · 231 per tool
Handshake
888 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 418

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

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