Ua1 Validator Agent

• Outcome: Pass
• Latest audit: Jul 25, 2026 · 10:33 PM UTC
• Version: 0.1.0

Overview

This skill does what it says: it validates user-selected PDFs by sending them to a remote PDF/UA-1 validation API, with no hidden persistence or unrelated behavior found.

Install this only if you are comfortable sending the PDFs you validate to api.ua1.dev or to whatever endpoint you set with UA1_API_BASE. Avoid using it on confidential, regulated, or customer documents unless you have checked the service’s data-handling terms and your organization permits that upload.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 82% confidence
• Finding: The skill instructs agents to execute a shell script (`bash scripts/validate_pdf.sh ...`) but does not declare corresponding permissions or clearly constrain shell usage. Hidden or undeclared execution capability increases the chance that an agent or reviewer underestimates what the skill can do, which weakens security review and policy enforcement.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill tells agents to upload PDF files to a third-party remote API for validation but provides no warning about privacy, confidentiality, retention, or data-handling implications. This can cause sensitive documents to be exfiltrated outside the local environment without informed operator consent, especially in CI or automated agent workflows.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The script uploads the provided PDF to a third-party remote service using curl, but it does not provide any runtime warning, consent prompt, or clear disclosure in the script output before transmitting potentially sensitive document contents. In an agent/CI context, this can silently exfiltrate confidential PDFs, making the behavior materially risky even if the feature is intentional.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Endpoints

- Health: `GET https://api.ua1.dev/api/health`
- Validate: `POST https://api.ua1.dev/api/validate`
- Compact mode: `POST https://api.ua1.dev/api/validate?format=compact`
- Metrics: `GET https://api.ua1.dev/api/metrics`

• Confidence: 97% confidence
• Finding: https://api.ua1.dev/

External Transmission

Medium

• Category: Data Exfiltration

Content

- Health: `GET https://api.ua1.dev/api/health`
- Validate: `POST https://api.ua1.dev/api/validate`
- Compact mode: `POST https://api.ua1.dev/api/validate?format=compact`
- Metrics: `GET https://api.ua1.dev/api/metrics`

## Required contract

• Confidence: 97% confidence
• Finding: https://api.ua1.dev/

External Transmission

Medium

• Category: Data Exfiltration

Content

TMP_BODY="$(mktemp)"
TMP_HEADERS="$(mktemp)"

HTTP_CODE="$(curl -sS -D "$TMP_HEADERS" -o "$TMP_BODY" -w '%{http_code}' \
  -X POST "$URL" \
  -F "file=@${FILE_PATH}")"

• Confidence: 94% confidence
• Finding: curl -sS -D

VirusTotal

52/52 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.