Back to skill

Security audit

remotion-shorts-skill

Security checks for vulnerabilities and agentic risk

Overview

The video workflow is clearly scoped, but an optional connection method puts a powerful social-posting key in a URL that could be exposed.

Prefer local-only rendering or the documented OAuth sign-in. Avoid the API-key-in-URL fallback, and rotate any key exposed through shared connection URLs, logs or configuration exports. Review the accounts, privacy and schedule before approving posts. Setup downloads packages and a browser and may require Linux system libraries. This review independently checked the material scanner gaps, but did not execute downloaded dependencies or verify the remote service.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Findings (12)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 187)May include surrounding context.

md
- [ ] Frame 0 shows the whole hook (check cuts.jpg); about 10 words or fewer, stating the payoff.
- [ ] Every scene says one thing; no scene over about 14 words.
- [ ] Every number matches its source; the source is on screen or in the caption.
- [ ] No warnings, or the user saw them and chose `--force`.
- [ ] Both sheets checked: no text outside the dashed safe line, highlights on the right words.
- [ ] 15 to 59 seconds.
- [ ] A distinct version for each account.

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · template/upload.mjs (reported line 2)May include surrounding context.

js
#!/usr/bin/env node
// Upload one file to a WoopSocial media upload session (no extra packages).
//
//   node upload.mjs session.json out/short/short.mp4
//

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · template/upload.mjs (reported line 46)May include surrounding context.

js
const res = await fetch(part.uploadUrl, { method: "PUT", body: chunk, headers: { "Content-Type": "application/octet-stream" } });
      if (res.ok) ok = true;
      else if (res.status === 403) {
        console.error(`Part ${part.partNumber} was refused (HTTP 403): the upload links have probably expired. Create a new upload session and run this again.`);
        process.exit(1);
      } else problem = `HTTP ${res.status}`;
    } catch (e) {

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: mcp, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

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 · evals/evals.json (reported line 8)May include surrounding context.

json
"id": 1,
      "prompt": "Make a 20 second TikTok about how much of the world's electricity came from solar last year. Use a real source.",
      "expected_output": "Finds a primary source (e.g. Ember or IEA), writes a hook plus 2 to 4 stat scenes with exact figures and the source in footer, runs --stills, checks sheet.jpg, renders the MP4, asks before posting.",
      "assertions": ["first scene is a hook", "every number matches the named source", "footer names the source", "render.mjs --stills run before the video", "no post without confirmation"]
    },
    {
      "id": 2,

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/platform-specs.md (reported line 62)May include surrounding context.

bash
# Ubuntu 24.04 (on 22.04 use libasound2 instead of libasound2t64)
sudo apt install -y libnss3 libdbus-1-3 libatk1.0-0 libasound2t64 libxrandr2 libxkbcommon-dev libxfixes3 libxcomposite1 libxdamage1 libgbm-dev libcups2 libcairo2 libpango-1.0-0 libatk-bridge2.0-0

# Debian 12
sudo apt install -y libnss3 libdbus-1-3 libatk1.0-0 libgbm-dev libasound2 libxrandr2 libxkbcommon-dev libxfixes3 libxcomposite1 libxdamage1 libpango-1.0-0 libcairo2 libcups2 libatk-bridge2.0-0

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/platform-specs.md (reported line 65)May include surrounding context.

sudo apt install -y libnss3 libdbus-1-3 libatk1.0-0 libasound2t64 libxrandr2 libxkbcommon-dev libxfixes3 libxcomposite1 libxdamage1 libgbm-dev libcups2 libcairo2 libpango-1.0-0 libatk-bridge2.0-0

Debian 12

sudo apt install -y libnss3 libdbus-1-3 libatk1.0-0 libgbm-dev libasound2 libxrandr2 libxkbcommon-dev libxfixes3 libxcomposite1 libxdamage1 libpango-1.0-0 libcairo2 libcups2 libatk-bridge2.0-0

text

## Remotion licence

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/woopsocial.md (reported line 27)May include surrounding context.

md
|---|---|
| Claude (claude.ai, Desktop, Cowork) | Add WoopSocial from the [Claude directory](https://claude.ai/directory/woopsocial), click Connect and sign in |
| Cursor | Install from [cursor.directory](https://cursor.directory/plugins/woopsocial-social-media-scheduler) and sign in |
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial` |
| OpenClaw | Install the [WoopSocial skill on ClawHub](https://clawhub.ai/woopsocial/skills/social-media-scheduler), or add the MCP URL to the agent's MCP config |
| Agents without sign-in support | Create an API key at [app.woopsocial.com/api-access](https://app.woopsocial.com/api-access) and use `https://api.woopsocial.com/mcp?api_key=%2A%2A%2A |

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/woopsocial.md (reported line 28)May include surrounding context.

md
| Claude (claude.ai, Desktop, Cowork) | Add WoopSocial from the [Claude directory](https://claude.ai/directory/woopsocial), click Connect and sign in |
| Cursor | Install from [cursor.directory](https://cursor.directory/plugins/woopsocial-social-media-scheduler) and sign in |
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial` |
| OpenClaw | Install the [WoopSocial skill on ClawHub](https://clawhub.ai/woopsocial/skills/social-media-scheduler), or add the MCP URL to the agent's MCP config |
| Agents without sign-in support | Create an API key at [app.woopsocial.com/api-access](https://app.woopsocial.com/api-access) and use `https://api.woopsocial.com/mcp?api_key=%2A%2A%2A |

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The fallback places a password-equivalent API key in the MCP URL query string. URLs can be retained in client configuration, diagnostics, proxy or server access logs, and support exports; disclosure could permit unauthorized access to the key's posting-service privileges despite HTTPS and the warning against sharing it.

Content

Scanner excerpt · references/woopsocial.md (reported line 30)May include surrounding context.

md
| Claude Code | `claude mcp add --transport http woopsocial "https://api.woopsocial.com/mcp"`, then `/mcp`, select woopsocial, Authenticate |
| Codex | `codex mcp add woopsocial --url https://api.woopsocial.com/mcp`, then `codex mcp login woopsocial` |
| OpenClaw | Install the [WoopSocial skill on ClawHub](https://clawhub.ai/woopsocial/skills/social-media-scheduler), or add the MCP URL to the agent's MCP config |
| Agents without sign-in support | Create an API key at [app.woopsocial.com/api-access](https://app.woopsocial.com/api-access) and use `https://api.woopsocial.com/mcp?api_key=%2A%2A%2A |

The API key is a password: never paste it into shared chats or commit it.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 · references/woopsocial.md (reported line 39)May include surrounding context.

md
and tells you when they're done. Confirm with `social_accounts_list`. Instagram needs a
professional (creator or business) account.

Find IDs yourself with `projects_list` and `social_accounts_list`; never ask the user to paste
IDs.

## 3. Upload the video

Stat formatting forces the en-US locale without a user-selectable locale.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The formatter explicitly uses toLocaleString("en-US", ...), imposing US numeric formatting on displayed statistics regardless of the user's locale. The file provides neither a locale choice nor a documented region-specific justification.

Content

No source excerpt is available for this finding.