Back to skill

Security audit

Veevid Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Veevid access is disclosed and includes clear user controls for spending, uploads, and permanent deletion.

Install if you are comfortable sending selected content to Veevid and authorizing paid generations. Keep the saved API key private, check model-specific credit adjustments, and review the exact creation before confirming permanent deletion. This artifact review does not verify the provider’s storage or retention practices.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
- `GET /api/credits` → `{"success": true, "credits": <n>, "balance": <n>}`
- `GET /api/user/creations?page=1&pageSize=20&includeAudio=1` — the user's past generations
- `DELETE /api/user/creations/{id}` — permanently removes a saved creation, its result files and, for some models, the uploaded input audio. Only when the user explicitly asks to delete that specific creation; show which one and get a yes first
- `POST /api/video-generation/{id}/upgrade-draft` — upgrade a Seedance 2.5 480p draft to 1080p. It spends credits: quote it with `{"draft_upgrade_id": "<id>"}` and get the user's confirmation first, like any generation

Details, response fields and every error code: [references/api-reference.md](references/api-reference.md).

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 46)May include surrounding context.

bash
(
  umask 077
  mkdir -p ~/.config/veevid
  chmod 700 ~/.config/veevid
  printf 'Veevid API key: '
  read -rs KEY; echo

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · SKILL.md (reported line 71)May include surrounding context.

bash
KEY=$(cat ~/.config/veevid/api_key)
BODY='{"mode":"veo3","generation_type":"text-to-video","prompt":"A golden retriever running through sunflowers, cinematic","video_quality":"standard","aspect_ratio":"16:9"}'
curl -X POST https://veevid.ai/api/quote -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" -d "$BODY"
# → {"required_credits":<n>,"current_balance":<n>,"sufficient":true}
# STOP: tell the user the model and <n> credits, and only continue after they say yes.

The skill exposes permanent deletion of saved creations and media, beyond its stated generation and editing purpose.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The manifest describes media generation, editing, pricing and credit checks, but this endpoint permanently deletes saved creations, result files and sometimes uploaded input audio. This is a separate destructive account-management capability, not a requirement for the advertised tasks; requiring explicit confirmation reduces accidental use but does not establish its relevance to the declared scope.

Content

No source excerpt is available for this finding.