Back to skill

Security audit

TimeToPost AutoSEO Blog

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the reported findings appear consistent with its stated purpose, though one reference could not be resolved and the scan is marked partial.

The verdict is benign, but benign does not mean risk-free. Skillspector’s scan is partial because it could not resolve a local path-like reference in SKILL.md; review the setup and the hosted MCP destination before connecting the skill.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
rch terms with `keyword_research` when useful. Explain that estimates are not measured search data. Call `autoseo_propose_topics` and show the proposed questions and rationale.
4. Get user approval for the topics. Configure with `autoseo_configure` using the approved topics and cadence. Never configure unattended publishing.
5. Use `autoseo_generate_post` for a topic the user approved. Read it with `read_article_draft`; inspect and improve it with `edit_article_draft`, then use `review_article_draft` as documented. Keep it a draft.
6. Show the final draft and request explicit approval before any publish-capable action. Do not call `update_article` or any other publish action without approval of the exact content and destination.
7. Run `seo_audit` or `geo_visibility_check` only if the connected server actually exposes those tools. These names do not appear in the provided tool references, so report them unavailable when absent. Never invent schemas or claim an audit was run.

## Safety

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/setup.md (reported line 3)May include surrounding context.

md
# Connect the TimeToPost MCP

Hosted MCP endpoint: `https://api.timetopost.co/mcp` with OAuth. For a client with remote Streamable HTTP support, add this URL and complete OAuth.

## Claude Code

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/setup.md (reported line 8)May include surrounding context.

Claude Code

sh
claude mcp add --transport http timetopost https://api.timetopost.co/mcp

Cursor

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/setup.md (reported line 14)May include surrounding context.

Cursor

json
{"mcpServers":{"timetopost":{"url":"https://api.timetopost.co/mcp"}}}

Codex

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/setup.md (reported line 21)May include surrounding context.

toml
[mcp_servers.timetopost]
url = "https://api.timetopost.co/mcp"

VS Code / Copilot

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/setup.md (reported line 27)May include surrounding context.

VS Code / Copilot

json
{"servers":{"timetopost":{"type":"http","url":"https://api.timetopost.co/mcp"}}}

The stdio option uses the official TimeToPost npm package and the user's API token from Settings → API, supplied through a local environment variable. Never paste a real token into chat or commit one to config. Confirm package and argument names against current official instructions before using stdio.