bidwire@1.0.0
CAUTION· install onlyPublisher claims: "Lets shopping agents turn a single purchase into a live auction where merchants bid, verifies every bid against the merchant's real product page and checkout, and ranks the surviving offers on merit rather than fees. It enforces spending limits with text-based human approval, then settles approved purchases in a double-entry ledger." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 6 of 6 bundled scripts run with no arguments, with decoy credentials in the environment · 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
INKBOX_API_KEYConfiguration, not credentials: APPROVER_PHONE, AUCTION_MS, BIDWIRE_DB, BIDWIRE_KEY, DIRECTOR_KEY, INKBOX_IDENTITY, PUBLIC_URL, RECEIPT_EMAIL- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- 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. It asks for INKBOX_API_KEY and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Access to sensitive file paths; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
printf '{"mcpServers":{"bidwire":{"type":"http","url":"%s","headers":{"Authorization":"Bearer %s"}}}}' "$URL" "${BIDWIRE_KEY:-bw_buy_claude_demo}" > "$CFG"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.<summary><b>Is it a real exchange?</b></summary> The mechanics are real: auctions run on timers, bids are verified by fetching storefront pages and checkout quoFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.try { process.loadEnvFile(".env"); } catch { /* ignore malformed .env */ }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>Anything else</b></summary> Any MCP client that speaks streamable HTTP can connect to `/mcp` directly; stdio-only clients can bridge with [`mcp-remoFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…k("b_chatgpt")}\nAuthentication: none\n(ChatGPT needs a public HTTPS URL: run \`npx mcp-use dev --tunnel\` or deploy to Manufact.)` }, { client: "codex", title: "Cod…Fix: Pin versions and sources; vendor anything fetched at install time.if (existsSync(".env")) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.printf '{"mcpServers":{"bidwire":{"type":"http","url":"%s"}}}' "$URL" > "$CFG"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Settings → Apps & Connectors → Advanced → Developer mode → Create connectorFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Settings → Apps & Connectors → Advanced → Developer mode → Create connectorFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim vnmoorthy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- 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.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.