ClawHub
Back to skill

Security audit

USDA FoodData Central API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward USDA nutrition lookup tool that sends user food queries and an FDC API key only to the documented USDA API.

Install this only if you are comfortable sending food search terms and your USDA FDC API key to the USDA FoodData Central API. Use a dedicated FDC API key, and remember the database is English-language and US-focused.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes shell scripts and makes outbound network requests, but the manifest does not declare any explicit tool scope such as allowed tools or permissions. This creates a least-privilege and auditability gap: a host may grant broader execution/network capability than users or reviewers expect, increasing the chance of unintended command execution or data egress.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation states that all food descriptions and search queries must be in English, which is a language restriction expressed in natural language. Under the policy rules, forcing a specific language without user opt-in is a language/locale policy violation unless it is clearly justified as a region-specific constraint with user choice, which is not provided here.

Content

No source excerpt is available for this finding.

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 45)May include surrounding context.

md
# Usage: fdc_search.sh "search query" [pageSize] [dataType]

# Configuration
API_BASE="https://api.nal.usda.gov/fdc/v1"

# Check for API key
if [ -z "$FDC_API_KEY" ]; then

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 · scripts/fdc_food.sh (reported line 6)May include surrounding context.

sh
# Usage: fdc_search.sh "search query" [pageSize] [dataType]

# Configuration
API_BASE="https://api.nal.usda.gov/fdc/v1"

# Check for API key
if [ -z "$FDC_API_KEY" ]; then

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 · scripts/fdc_search.sh (reported line 6)May include surrounding context.

sh
# Usage: fdc_search.sh "search query" [pageSize] [dataType]

# Configuration
API_BASE="https://api.nal.usda.gov/fdc/v1"

# Check for API key
if [ -z "$FDC_API_KEY" ]; then

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · scripts/fdc_search.sh (reported line 47)May include surrounding context.

sh
fi

# Make API request
RESPONSE=$(curl -s -w "\n%{http_code}" -X POST \
    -H "Content-Type: application/json" \
    -H "X-Api-Key: $FDC_API_KEY" \
    -d "$JSON_PAYLOAD" \

Static analysis

No suspicious patterns detected.