ClawHub
Back to skill

Security audit

contentdrips

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently connects OpenClaw to ContentDrips for social design and publishing, with disclosed external account actions and confirmation rules for publishing and deletion.

Install only if you trust ContentDrips with the API token and the connected LinkedIn/Instagram accounts. Review requests carefully when the agent proposes publishing, scheduling, deleting, or choosing a workspace/profile, and prefer explicit platform wording such as 'publish to LinkedIn only'.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
# ContentDrips MCP Skill

ContentDrips MCP connects your agent to [ContentDrips](https://contentdrips.com) — create designs, generate AI carousels/graphics, run the AI Design Agent, manage posts, and publish to LinkedIn and Instagram through conversation.

**MCP URL:** `https://mcp.contentdrips.com/mcp`

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad everyday terms such as "design," "template," "LinkedIn," and "Instagram," which can cause the skill to activate in contexts where the user did not clearly intend to use this external MCP integration. Unintended invocation is risky here because the skill can create content, manage posts, and potentially lead toward publishing actions in an external service.

Content

No source excerpt is available for this finding.

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
## Agent rules

1. **Workspaces first (always)** — call `get_profiles` before `create_graphic`, `create_post`, `generate_*`, `render_template`, schedule, or publish. If 2+ workspaces, ASK which. Always pass `profile_id`. Never tell the user you lack a profile_id — fetch it.
2. **MAIN FLOW — route by whether they named a template** (template = design = graphic = carousel = infographic):
   - **No ID or name:** AI Design Agent. `get_profiles` → `create_graphic(profile_id)` → `get_brand_styles` (if 2+ ASK which) → `run_ai_design_agent` (pass `reference_image` if they uploaded a picture) → **share the editor link and STOP**.
   - **Has ID or name:** AI maker (keep layout). `get_template` → `get_template_structure` → `generate_ai_carousel` / `generate_ai_graphic` → `check_job_status`.

Static analysis

No suspicious patterns detected.