ClawHub
Back to skill

Security audit

CVS Product Data API - Prices, Coupons, Store Stock

Security checks for vulnerabilities and agentic risk

Overview

The skill’s CVS product lookups use a clearly disclosed third-party service and fit its stated purpose.

Scavio receives your search terms, product selections, and store number; avoid including personal medical details. Keep the API key in secret storage and remember that requests consume credits. Direct API calls avoid installing the optional SDK or MCP server. If enabling MCP, review its additional tools and protect its saved credentials. This review covers the supplied instructions, not Scavio’s server implementation or external package code.

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
  • 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 user search terms and store selections to Scavio without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The workflow instructs the agent to transmit search queries, store IDs, and product selections to Scavio, a third-party service. Although the API destination is documented, the skill does not warn users that their shopping queries and chosen store are shared externally; health-product searches can disclose sensitive interests.

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 104)May include surrounding context.

Examples

bash
curl -X POST https://api.scavio.dev/api/v1/cvs/stock \
  -H "Authorization: Bearer $SCAVIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"store_id": "7019", "sku_ids": ["832677", "854346", "396475", "275748", "874110"]}'

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 104)May include surrounding context.

Examples

bash
curl -X POST https://api.scavio.dev/api/v1/cvs/stock \
  -H "Authorization: Bearer $SCAVIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"store_id": "7019", "sku_ids": ["832677", "854346", "396475", "275748", "874110"]}'

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 184)May include surrounding context.

md
def cvs(endpoint, body):
    # /product can take 10-30+ seconds; a generous timeout keeps it from failing early.
    r = requests.post(f"{BASE}/api/v1/cvs/{endpoint}", headers=HEADERS, json=body, timeout=120)
    r.raise_for_status()
    return r.json()["data"]