Back to skill

Security audit

Shipyard video

Security checks for vulnerabilities and agentic risk

Overview

The video workflow includes useful safeguards, but it can expand into broader app changes and loosen sign-in rules beyond the video files.

Review the full Shipyard plugin before installing. Approve broader app upgrades separately, restrict public access exceptions to intended video paths, preserve master renders, and use installed, pinned tooling. Voice generation sends approved narration to the selected provider and incurs disclosed costs.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

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 · SKILL.md (reported line 27)May include surrounding context.

md
## Rules (always)

- You do the work. Run the scripts and commands yourself. The student reads the script, listens to the key lines, says yes, and watches the result.
- Never ask for keys in the chat and never read `~/.shipyard/secrets.env` or any `.env*` file (including `video/.env`; there is none). Keys go in the Shipyard keys file (`node "${CLAUDE_PLUGIN_ROOT}/scripts/secrets-init.mjs"` opens it). The voice script hands them to the engine privately and prints only names.
- Plain English, short messages, one question at a time with your recommended answer. Explain any new word in five words or fewer.
- **The script is approved before any voice is made.** Voice costs a few cents per minute and every re-voice costs again.
- Verify with your own eyes: look at stills and the contact sheet with the Read tool. Do not hand image checks to a helper. Say what you checked and what you did not.

Standalone triggers such as "video", "promo", and "explainer" are broader than the app-video workflow.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The activation list includes generic words that can occur in requests to discuss, review, or explain videos rather than create a product video. Although the description identifies an app-video purpose, it explicitly accepts these broad triggers without requiring creation intent or excluding unrelated requests.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx tsc'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx tsc'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

The finishing workflow directs deletion of old renders without warning the user about losing previous outputs.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The finishing step directs deletion of old renders without defining which outputs are disposable or obtaining approval. Earlier approvals for scripts, GitHub, and publishing do not authorize deleting prior deliverables, so following this step could destroy versions the user intended to retain.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx tsc'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx playwright'.

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

The instruction runs npx playwright in the app folder without ensuring a pinned local Playwright dependency exists there. If it is absent, npx can offer to download and execute a registry-selected version, introducing an unnecessary supply-chain execution risk; the tool is not an MCP server, but the fallback risk is real.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx tsc'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.