Skills/Glama/thingery

thingery@0.2.0

CAUTION· install only

Publisher claims: "Thingery is the open item database and MCP server for AI agents to list, find, and trade second-hand goods. Agents publish listings with photos and category attributes, search via hybrid semantic/keyword filters, and connect to the hosted instance or self-host with Postgres + pgvector (npx thingery over stdio)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher thingery · publishing for 1 daysInstalls 0Last detonated 20 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution 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
ADMIN_API_KEYDATABASE_URLEASYPOST_WEBHOOK_SECRETEMBED_API_KEYLLM_API_KEYOAUTH_ACCESS_TTL_SOAUTH_DCR_HOURLY_LIMITOAUTH_DISABLEDOAUTH_REFRESH_TTL_SOPENAI_APPS_CHALLENGE_TOKENROUTINE_WEBHOOK_TOKENSELLER_API_KEYSESSION_SECRETSTRIPE_SECRET_KEYSTRIPE_WEBHOOK_SECRETTHINGERY_API_KEYConfiguration, not credentials: ADMIN_KEY, B_KEY, DEMO_SELLER_KEY, EMBED_API_URL, EMBED_MODEL, FRAMES_DIR, LLM_API_URL, LLM_BYO_ALLOW_LOCAL_ENDPOINTS, LLM_BYO_ALLOWED_MODELS, LLM_MODEL, O_KEY, OUT, PROBE_KEY, PUBLIC_BASE_URL, S_KEY, THINGERY_MCP_URL, TRANSPORT, UPLOADS_DIR
Where it talks to
thingery.dev (its own)Also easypost.com, z.ai, soldstack.dev — 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
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names easypost.com, z.ai, soldstack.dev as well as its own vendor. The guard injects ADMIN_API_KEY, DATABASE_URL, EASYPOST_WEBHOOK_SECRET, EMBED_API_KEY, LLM_API_KEY, OAUTH_ACCESS_TTL_S, OAUTH_DCR_HOURLY_LIMIT, OAUTH_DISABLED, OAUTH_REFRESH_TTL_S, OPENAI_APPS_CHALLENGE_TOKEN, ROUTINE_WEBHOOK_TOKEN, SELLER_API_KEY, SESSION_SECRET, STRIPE_SECRET_KEY, STRIPE_WEBHOOK_SECRET, THINGERY_API_KEY only into requests to thingery.dev (and its subdomains) and refuses the rest.

$vet-skills run --secrets ADMIN_API_KEY=thingery.dev,DATABASE_URL=thingery.dev,EASYPOST_WEBHOOK_SECRET=thingery.dev,EMBED_API_KEY=thingery.dev,LLM_API_KEY=thingery.dev,OAUTH_ACCESS_TTL_S=thingery.dev,OAUTH_DCR_HOURLY_LIMIT=thingery.dev,OAUTH_DISABLED=thingery.dev,OAUTH_REFRESH_TTL_S=thingery.dev,OPENAI_APPS_CHALLENGE_TOKEN=thingery.dev,ROUTINE_WEBHOOK_TOKEN=thingery.dev,SELLER_API_KEY=thingery.dev,SESSION_SECRET=thingery.dev,STRIPE_SECRET_KEY=thingery.dev,STRIPE_WEBHOOK_SECRET=thingery.dev,THINGERY_API_KEY=thingery.dev -- <the server's command>

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 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: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. 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
Access to sensitive file pathssrc/llm-credentials.ts:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files/** env name, kept in one place for .env.example / compose / docs alignment. */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/render-demo-video.py:221 · Python subprocess execution detectedsubprocess.run(["ffmpeg", "-y", "-r", str(FPS), "-i", os.path.join(FRAMES_DIR, "f%05d.png"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/auth.ts:96 · Process kill command — agent can terminate processes* (revoked grants kill their tokens) — no fallback chain, no second query.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/llm-guard.sh:66 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$STATE_DIR" && chmod 700 "$STATE_DIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandsrc/auth.ts:146 · Process kill command — agent can terminate processes/** OAUTH_DISABLED kill switch (spec THI-11 §4.4): read per call so it can beFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/config.ts:6 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// everywhere. HMAC-SHA256(body, "") is computable by anyone, and .env filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsAGENTS.md:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslogs, or PR descriptions. Use `.env.example` placeholders only.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsAGENTS.md:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. **Credentials never enter the repo.** No tokens, no `.env` files, no secrets in code,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/render-demo-video.py:202 · npx invocation of non-well-known package — may execute untrusted coded.text((W//2, 470), "same flow self-hosted: npx thingery · MCP: thingery.dev/mcp",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/routes.ts:556 · File type combined with upload action — agent may exfiltrate local data filesres.status(429).json({ error: "Too many uploads — try again later." });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/config.ts:38 · Process kill command — agent can terminate processes* A2): 0 is a MEANINGFUL value — LABEL_DAILY_BUDGET_CENTS=0 is the spend killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/auth.ts:177 · Process kill command — agent can terminate processesif (oauthDisabled()) return { seller: null, failure: "invalid_token" }; // kill switch (§4.4)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/config.ts:164 · Process kill command — agent can terminate processesconsole.log("[config] Stripe payments not configured — order tools answer payments_not_configured (kill switch)");Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/fulfillment.ts:141 · Process kill command — agent can terminate processes// LABEL_DAILY_BUDGET_CENTS (default €200; 0 = kill switch), derived fromFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/mcp-gate.ts:311 · File type combined with upload action — agent may exfiltrate local data filesres.status(405).json({ error: "Method not allowed. Use POST with JSON-RPC. Stateles HTTP transport." });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/routes.ts:572 · File type combined with upload action — agent may exfiltrate local data filesres.status(400).json({ error: "Empty upload — send the image bytes as the request body." });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/fulfillment.ts:365 · Process kill command — agent can terminate processes// controls”): 0 = kill switch — every purchase is refused while tracker-onlyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stripe.ts:20 · Process kill command — agent can terminate processes// The client is null when Stripe is unconfigured (config.ts kill switch) —Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/index.ts:52 · npx invocation of non-well-known package — may execute untrusted code* TRANSPORT=stdio — local MCP server over stdin/stdout, for `npx thingery` andFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandsrc/oauth.ts:220 · Process kill command — agent can terminate processes// OAUTH_DISABLED kill switch (spec §4.4): no OAuth route is mounted at all —Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/stripe.ts:30 · Process kill command — agent can terminate processes/** Singleton Stripe client; null when STRIPE_SECRET_KEY is unset (kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/webhooks-stripe.ts:3 · File type combined with upload action — agent may exfiltrate local data files// Mount BEFORE the global express.json() (index.ts) — signatures are computedFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/config.ts:173 · File type combined with upload action — agent may exfiltrate local data filesconsole.log("[config] Admin dispute route disabled (ADMIN_API_KEY unset or shorter than 32 chars)");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/version.ts:15 · File type combined with upload action — agent may exfiltrate local data files* The Dockerfile writes a `build-info.json` next to the compiled outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/routes.ts:692 · File type combined with upload action — agent may exfiltrate local data filesres.status(400).json({ error: `Send images as an array of up to ${MAX_IMAGES_PER_ITEM} photo references.` });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/config.ts:89 · Process kill command — agent can terminate processeslabelDailyBudgetCents: number; // 20000 ≈ €200/day platform-wide; 0 = kill switch (A2)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/routes.ts:538 · File type combined with upload action — agent may exfiltrate local data filesres.status(429).json({ error: "Too many uploads — try again later." });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/config.ts:51 · Process kill command — agent can terminate processes// Stripe payments (the kill switch: STRIPE_SECRET_KEY absent → order toolsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/routes.ts:568 · File type combined with upload action — agent may exfiltrate local data filesres.status(400).json({ error: "Send the image bytes as the raw request body with an image Content-Type." });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/chatgpt-oauth.ts:191 · Process kill command — agent can terminate processes// --- refresh (§3.3): single-flight, compare-and-swap, terminal-error kill ---Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/routes.ts:103 · Process kill command — agent can terminate processes// escaping as unhandled rejections that kill the process (Express 4 does notFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,101 tok
3 files · 80 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 thingery: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  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 thingeryPropose a patch to the maintainer