Back to skill

Security audit

Facebook API

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-aligned, but it handles the JustOneAPI token in command arguments and URL query parameters, which can expose the token in logs or process listings.

Install only if you are comfortable sending Facebook lookup/search inputs and a JustOneAPI token to JustOneAPI. Prefer a token with limited scope and quota, rotate it if exposed, and avoid logging full command lines or request URLs while using this skill.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
bin/run.mjs:173
Finding

API Credential Exposed Through Process Arguments and URL Query Parameters

Content
View full analysis
" --token "$JUST_ONE_API_TOKEN" --params-json '{"key":"value"}' ``` The operation manifest declares the credential as a query parameter: ```js { "defaultValue": null, "description": "User security token for API access authentication.", "enumValues": [], "location": "query", "name": "token", "required": true, "schemaType": "string" } ``` The helper accepts the token from the command line and inserts it into the operation parameters: ```js function parseArgs(argv) { const parsed = { operation: null, paramsJson: "{}", token: null }; for (let index = 0; index < argv.length; index += 1) { const flag = argv[index]; const value = argv[index + 1]; if (flag === "--operation") { parsed.operation = value; index += 1; continue; } if (flag === "--params-json") { parsed.paramsJson = value; index += 1; continue; } if (flag === "--token") { parsed.token = value; index += 1; continue; } fail(`Unknown argument "${flag}".`); } return parsed; } function injectToken(operation, params, cliToken) { const tokenParam = operation.parameters.find((parameter) => parameter.name === "token"); if (!tokenParam || params.token !== undefined) { return; } if (!cliToken) { fail("--token is required for this operation.", { operationId: operation.operationId, }); } params.token = cliToken; } ``` All query parameters, including `tok ...[truncated 3956 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

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 · SKILL.md (reported line 53)May include surrounding context.

md
- Get a token from [Just One API Dashboard](https://dashboard.justoneapi.com/en/login?utm_source=clawhub.ai&utm_medium=referral&utm_campaign=justoneapi_facebook&utm_content=project_link).
- Authentication details: [Just One API Usage Guide](https://docs.justoneapi.com/en/?utm_source=clawhub.ai&utm_medium=referral&utm_campaign=justoneapi_facebook&utm_content=project_link).

## Output Rules

- Start with a plain-language answer tied to the Facebook task the user asked for.
- Include the most decision-relevant fields from the selected endpoint before dumping raw JSON.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes a Node helper that performs authenticated external API requests, but the manifest does not declare an explicit tool scope such as allowed network access or permissions. This weakens policy enforcement and reviewability because a host system cannot clearly constrain or validate the skill's network behavior before execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The API authentication token is defined as a query parameter and is automatically appended to the request URL. Query-string secrets are commonly exposed through logs, browser/history artifacts, proxy layers, monitoring systems, and upstream service telemetry, making credential leakage more likely even when HTTPS is used. In this skill context, the token is the primary credential for a third-party API, so accidental disclosure could allow unauthorized API use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The API authentication token is defined as a required query parameter, which increases the chance of credential exposure through logs, browser history, proxy caches, analytics systems, and referrer leakage. Even over HTTPS, placing secrets in the URL is an unsafe design choice because many downstream systems record full request URIs by default.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file documents a required token query parameter for an API call, which means the skill will transmit user credentials over a network request. The file does not include any user-facing warning about handling sensitive tokens, privacy implications, or avoiding accidental exposure in URLs/query strings.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This section again requires a token query parameter for a networked Facebook-related API operation, but the markdown provides no warning about sending sensitive authentication data to an external service. For markdown files, omission of warnings about privacy- or credential-affecting behavior is in scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The endpoint description requires a security token and performs a remote search request, but there is no warning that sensitive credentials are being transmitted or that search terms may be sent to an external API. The markdown should disclose these privacy-relevant behaviors to users.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The script sends network requests to an external API using profile URLs, profile IDs, search keywords, cursors, and authentication tokens assembled from CLI input. Although network access is central to the skill's purpose, this file does not contain any explicit user-facing notice or comment explaining that supplied data will be transmitted to a third-party service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill description and operation descriptions present Facebook profile lookup, post retrieval, and post search as simple analysis features, but do not warn that user-supplied identifiers and search terms are sent to an external API service. For markdown/manifest-style descriptions, omission of data-transmission warnings for external services can leave users unaware of privacy-impacting behavior.

Content

No source excerpt is available for this finding.