Back to skill

Security audit

gogcli-mcp-calendar

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because its Calendar and Meet purpose is accompanied by broader permissions and actions, including whole-calendar deletion and Zoom credential management.

Consider the verdict suspicious and review the reported broader access and actions before installing. In particular, assess whether you need whole-calendar deletion, Zoom credential management, and authorization beyond Calendar and Meet; scan coverage was partial, and dependency versions were not verified.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (43)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Most tested Calendar event and Meet operations match the description. However, Zoom authentication management concerns an undeclared service and credential-management capability. Deleting or unsubscribing from entire calendars also exceeds the stated scope of managing calendar events. These capabilities are explicitly represented by tool calls and expected CLI arguments, although their real execution is not demonstrated because runOrDiagnose is mocked.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Most tools align with the declared Calendar-event and Meet-space purpose. However, Zoom credential administration introduces an undeclared external service and persistent credential-management capability. Calendar unsubscription and whole-calendar deletion also exceed the stated event-management scope; deletion is explicitly implemented with a confirmation flow followed by calendar delete-calendar --force. These are exposed capabilities, not merely supporting implementation details. Confirmation safeguards do not resolve the description mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Event moves and out-of-office invitation handling fit the declared event-management purpose, and their confirmation mechanisms are supporting implementation details. However, the suite explicitly exercises gog_calendar_delete_calendar, which deletes the calendar resource itself and every event on it. That broader destructive capability is not disclosed by a description limited to managing events and Meet spaces. Because the command runner is mocked, this chunk demonstrates tests for that capability rather than actual calendar deletion.

Content

No source excerpt is available for this finding.

YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedded in AI agent skill text [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · dist/index.js (reported line 43)May include surrounding context.

js
../node_modules/@chrischall/mcp-utils/dist/caller/index.js
import { AsyncLocalStorage as AsyncLocalStorage2 } from "node:async_hooks";
var storage2 = new AsyncLocalStorage2();
function withCallerCapabilities(capabilities, fn) {
  return capabilities ? storage2.run(capabilities, fn) : fn();
}
function currentCallerCapabilities() {
  return storage2.getStore();
}
var ENVELOPE_CAPABILITIES_KEY = "io.modelcontextprotocol/clientCapabilities";
var ELICITATION_MODES = ["form", "url"];
function isRecord(value) {
  return typeof value === "object" && value !== null && !Array.isArray(value);
}
function callerCapabilities(ctx) {
  const envelope = isRecord(ctx) && isRecord(ctx.mcpReq) ? ctx.mcpReq.envelope : void 0;
  if (isRecord(envelope)) {
    const declared = envelope[ENVELOPE_CAPABILITIES_KEY];
    if (isRecord(declared))
      return declared;
  }
  return currentCallerCapabilities();
}
function callerAcceptsFormElicitation(ctx) {
  const capabilities = callerCapabilities(ctx);
  if (!capa

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · dist/index.js (reported line 27151)May include surrounding context.

js
function validateAsync3() {
      const ruleErrs = gen.let("ruleErrs", null);
      gen.try(() => assignValid((0, codegen_1._)`await `), (e) => gen.assign(valid, false).if((0, codegen_1._)`${e} instanceof ${it.ValidationError}`, () => gen.assign(ruleErrs, (0, codegen_1._)`${e}.errors`), () => gen.throw(e)));
      return ruleErrs;
    }
    function validateSync() {
      const validateErrs = (0, codegen_1._)`${validateRef}.errors`;

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · dist/index.js (reported line 33978)May include surrounding context.

js
if (typeof promptName !== "string") return;
        const prompt = this._registeredPrompts[promptName];
        if (prompt === void 0 || !prompt.enabled) return;
        return prompt.scopeChallenge?.(context);
      }
      default:
        return;

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · dist/index.js (reported line 34180)May include surrounding context.

js
const prompt = this._registeredPrompts[request.params.name];
      if (!prompt) throw new ProtocolError(ProtocolErrorCode.InvalidParams, `Prompt ${request.params.name} not found`);
      if (!prompt.enabled) throw new ProtocolError(ProtocolErrorCode.InvalidParams, `Prompt ${request.params.name} disabled`);
      return prompt.handler(request.params.arguments, ctx);
    });
    this._promptHandlersInitialized = true;
  }

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · dist/index.js (reported line 35309)May include surrounding context.

js
return walk(value, keep, drop);
}
function normalizeRules(rules) {
  return rules.map((rule) => typeof rule === "string" ? rule.toLowerCase() : new RegExp(rule.source, rule.flags));
}
function matchesRule(key, rules) {
  const lower = key.toLowerCase();

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · dist/index.js (reported line 36707)May include surrounding context.

js
var TOKEN_LEFT_BOUNDARY = "(?<![A-Za-z0-9+/])";
var GOOGLE_TOKEN_PATTERNS = [
  new RegExp(`${TOKEN_LEFT_BOUNDARY}ya29\\.[A-Za-z0-9._\\-]+`, "g"),
  // OAuth2 access tokens
  new RegExp(`${TOKEN_LEFT_BOUNDARY}1//[A-Za-z0-9._\\-]+`, "g")
  // OAuth2 refresh tokens
];

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · dist/index.js (reported line 37364)May include surrounding context.

js
}
  });
  server.registerTool("gog_auth_status", {
    description: "Show gogcli auth CONFIGURATION: keyring backend, credential files, and auth setup. Despite the name this is not a health check \u2014 it reads local setup and does not contact Google, so it says nothing about whether an account can still authenticate. Use gog_auth_health for that.",
    annotations: { readOnlyHint: true, openWorldHint: false },
    inputSchema: external_exports.object({})
  }, async () => {

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 22)May include surrounding context.

yaml
required: false
    help: >-
      Google OAuth client id. Read by the Node wrapper at startup
      (bootstrap-auth.ts), which imports it into gog's keyring via a temp file
      together with GOG_CLIENT_SECRET, GOG_REFRESH_TOKEN and GOG_ACCOUNT — set
      all four or none. Not a secret, so unlike GOG_CLIENT_SECRET and
      GOG_REFRESH_TOKEN it is not stripped from the spawned `gog`'s

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 66)May include surrounding context.

yaml
secret: true
    required: false
    help: >-
      Encrypts gog's file keyring on the data dir. Required with
      GOG_KEYRING_BACKEND=file. Deliberately not stripped from the spawned
      CLI's environment — it is the one credential gog itself reads.
  - name: GOG_READONLY

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · dist/index.js (reported line 37375)May include surrounding context.

js
}
  });
  server.registerTool("gog_auth_health", {
    description: `Check the LIVE health of each stored Google account. Unlike gog_auth_status (which only reports keyring/config setup), this performs a real token refresh against Google, so it detects expired or revoked (invalid_grant) refresh tokens \u2014 the account-wide sign-out that blocks every service. Reports per account: whether the token is currently valid, the mapped cause when it is not, how long ago it was authorized, and a warning as it approaches the 7-day refresh-token limit that applies to OAuth apps whose consent screen is still in "Testing" mode. Run it proactively to re-authorize on your own schedule instead of mid-task. On a hosted deployment this is the ONLY check that measures Google: a connector showing "connected" or "refreshed" has verified the client's connection to the MCP host, and nothing else \u2014 the Google credential lives in gog's keyring on that host and can be dead while the connection looks p

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · dist/index.js (reported line 37375)May include surrounding context.

js
tus (which only reports keyring/config setup), this performs a real token refresh against Google, so it detects expired or revoked (invalid_grant) refresh tokens \u2014 the account-wide sign-out that blocks every service. Reports per account: whether the token is currently valid, the mapped cause when it is not, how long ago it was authorized, and a warning as it approaches the 7-day refresh-token limit that applies to OAuth apps whose consent screen is still in "Testing" mode. Run it proactively to re-authorize on your own schedule instead of mid-task. On a hosted deployment this is the ONLY check that measures Google: a connector showing "connected" or "refreshed" has verified the client's connection to the MCP host, and nothing else \u2014 the Google credential lives in gog's keyring on that host and can be dead while the connection looks perfectly healthy.`,
    annotations: { readOnlyHint: true, openWorldHint: true },
    inputSchema: external_exports.object({})
  }, async () => {

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 26)May include surrounding context.

yaml
together with GOG_CLIENT_SECRET, GOG_REFRESH_TOKEN and GOG_ACCOUNT — set
      all four or none. Not a secret, so unlike GOG_CLIENT_SECRET and
      GOG_REFRESH_TOKEN it is not stripped from the spawned `gog`'s
      environment; gog authenticates from its keyring under $HOME (see
      state.dataDir).
  - name: GOG_CLIENT_SECRET
    secret: true

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 32)May include surrounding context.

yaml
secret: true
    required: false
    help: >-
      Google OAuth client secret. Imported into gog's keyring at startup with
      GOG_CLIENT_ID; stripped from the spawned CLI's environment by runner.ts's
      *_SECRET rule.
  - name: GOG_REFRESH_TOKEN

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 40)May include surrounding context.

yaml
required: false
    help: >-
      Google OAuth refresh token (`gog auth tokens export` prints one). Imported
      into gog's keyring at startup with GOG_CLIENT_ID; stripped from the
      spawned CLI's environment by runner.ts's *_TOKEN rule. Changing it
      re-imports on the next start; an in-connector re-auth
      (gog_auth_add_url/complete) stays in effect until it changes.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 61)May include surrounding context.

yaml
required: false
    help: >-
      gog's credential store. Set to "file" on a headless host — there is no OS
      keychain — so the keyring lives on the persistent data dir.
  - name: GOG_KEYRING_PASSWORD
    secret: true
    required: false

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 107)May include surrounding context.

yaml
state:
  dataDir: true
  reason: >-
    `gog` keeps its authorised-account state and file keyring under $HOME, and
    the wrapper keeps its auth-bootstrap marker (~/.gogcli-mcp) there, so a
    restart neither re-imports an unchanged secret nor discards an
    in-connector re-auth. Without a persistent data dir every cold start has

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · dist/index.js (reported line 38137)May include surrounding context.

js
return runOrDiagnose(args, { account });
  });
  server.registerTool("gog_zoom_auth_setup", {
    description: "Store Zoom Server-to-Server (S2S) OAuth credentials so calendar events can be attached to Zoom meetings via the --with-zoom flag on gog_calendar_create / gog_calendar_update. Credentials are saved in gogcli's keyring under the given alias.",
    annotations: { destructiveHint: true, openWorldHint: true },
    inputSchema: external_exports.object({
      accountId: external_exports.string().describe("Zoom S2S OAuth account ID"),

The skill can permanently delete an entire calendar, beyond its declared event-management scope.

High
Category
Excessive Agency
Confidence
95% confidence
Finding

The manifest describes managing Calendar events and Meet spaces, but gog_calendar_delete_calendar executes calendar delete-calendar --force at L38412, deleting the calendar container and every event on it. The confirmation flow protects against accidental execution but does not resolve the mismatch between event-level management and calendar-wide destruction.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 57)May include surrounding context.

yaml
The Google account to act as. Required for the startup auth bootstrap
      (the refresh token is imported under this email); otherwise defaults to
      gog's single/most recent account.
  - name: GOG_KEYRING_BACKEND
    required: false
    help: >-
      gog's credential store. Set to "file" on a headless host — there is no OS

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 62)May include surrounding context.

yaml
help: >-
      gog's credential store. Set to "file" on a headless host — there is no OS
      keychain — so the keyring lives on the persistent data dir.
  - name: GOG_KEYRING_PASSWORD
    secret: true
    required: false
    help: >-

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 61)May include surrounding context.

yaml
required: false
    help: >-
      gog's credential store. Set to "file" on a headless host — there is no OS
      keychain — so the keyring lives on the persistent data dir.
  - name: GOG_KEYRING_PASSWORD
    secret: true
    required: false

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · mint.yaml (reported line 67)May include surrounding context.

yaml
required: false
    help: >-
      Encrypts gog's file keyring on the data dir. Required with
      GOG_KEYRING_BACKEND=file. Deliberately not stripped from the spawned
      CLI's environment — it is the one credential gog itself reads.
  - name: GOG_READONLY
    required: false