Back to skill

Security audit

HEB Grocery Data API - Search, Product Detail, Store Locator

Security checks for vulnerabilities and agentic risk

Overview

The skill provides grocery lookups through Scavio with expected API access and no evidence of hidden or harmful behavior.

Scavio receives your searches and any ZIP code or city you supply. Its [privacy policy](https://scavio.dev/privacy) says request logs, including queries, remain for up to 90 days. Protect your API key and monitor credit usage. Optional SDK/MCP package code was not audited; direct API calls avoid those dependencies and the MCP example's extra platforms.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

The workflow sends the shopper's location to Scavio without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to submit the shopper's ZIP code or city to the store endpoint hosted by Scavio, a third-party service. Although the API provider is identified elsewhere, the skill never instructs the agent to warn the user that their location and subsequent shopping queries are transmitted to that provider.

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 139)May include surrounding context.

Examples

bash
curl -X POST https://api.scavio.dev/api/v1/heb/search \
  -H "Authorization: Bearer $SCAVIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "whole milk", "store_id": "441", "page_size": 5}'

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 · SKILL.md (reported line 139)May include surrounding context.

Examples

bash
curl -X POST https://api.scavio.dev/api/v1/heb/search \
  -H "Authorization: Bearer $SCAVIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "whole milk", "store_id": "441", "page_size": 5}'

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 · SKILL.md (reported line 194)May include surrounding context.

md
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

def heb(endpoint, body):
    r = requests.post(f"{BASE}/api/v1/heb/{endpoint}", headers=HEADERS, json=body)
    r.raise_for_status()
    return r.json()["data"]