mcp@0.4.28
CAUTION· install onlyPublisher claims: "Model Context Protocol (MCP) server for the Lightsage Public API." 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
- 5 of 5 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
CLERK_SECRET_KEYLIGHTSAGE_API_KEYLIGHTSAGE_API_KEY_AUTHLIGHTSAGE_LIGHTSAGE_API_KEY_AUTHLIGHTSAGE_MCP_TRACKER_API_KEYMCP_EXCHANGE_SECRETMCP_OAUTH_ENABLEDor--lightsage-api-key-authConfiguration, not credentials: CLERK_PUBLISHABLE_KEY, LIGHTSAGE_EXCHANGE_URL, MCP_RESOURCE_URL- Where it talks to
- lightsage.com (its own)Also speakeasy.com, usesapient.com, gstatic.com, cursor.com — not the publisher's domain; check what for before connecting.
- 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, and read the third-party hosts first. The code names speakeasy.com, usesapient.com, gstatic.com, cursor.com as well as its own vendor. The guard injects CLERK_SECRET_KEY, LIGHTSAGE_API_KEY, LIGHTSAGE_API_KEY_AUTH, LIGHTSAGE_LIGHTSAGE_API_KEY_AUTH, LIGHTSAGE_MCP_TRACKER_API_KEY, MCP_EXCHANGE_SECRET, MCP_OAUTH_ENABLED only into requests to lightsage.com (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.4.25
vet-skills diff mcp 0.4.25 0.4.28In the sandbox, this version reached for nothing 0.4.25 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 2026-11-19 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; Collapsed <details> block carrying instructions; URL with embedded credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
globals.process?.env ?? globals.Deno?.env?.toObject?.() ?? {},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<code class="code-snippet language-json" id="claude-cli-cmd">claude mcp add LightsageMcp -- npx -y @lightsage/mcp start --lightsage-api-key-auth </code>Fix: Pin versions and sources; vendor anything fetched at install time.<summary> Stdio installation via npm </summary> To start the MCP server, run: ```bash npx @lightsage/mcp start --lightsage-api-key-auth ``` For a full list of sFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<code class="code-snippet language-json" id="gemini-config">gemini mcp add LightsageMcp -- npx -y @lightsage/mcp start --lightsage-api-key-auth </code>Fix: Pin versions and sources; vendor anything fetched at install time.<link href="https://fonts.googleapis.com/css2?family=Geist+Mono:[email protected]&family=Geist:[email protected]&display=swap" rel="stylesheet">Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
No advisories in OSV for @lightsage/mcp@0.4.28 as of 8 h ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim lightsage: 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.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.