Back to skill

Security audit

Poyo Claude Sonnet 5

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PoYo API integration helper that sends prepared Claude Messages payloads only when the user chooses to make an API call.

Install this only if you intend to use PoYo's Claude Sonnet 5 API. Treat POYO_API_KEY as a secret, review payload files before submitting them, and avoid sending private prompts, images, or tool inputs unless that is acceptable for your PoYo account and data policy.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/api.md (reported line 19)May include surrounding context.

Content-Type: application/json

text

Get API keys from <https://poyo.ai/dashboard/api-key>.

Recommended skill env var:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill declares a shell-capable dependency (curl) but does not define any explicit tool scope such as allowed tools or permissions. That leaves execution boundaries implicit, increasing the chance that an agent can invoke shell behavior more broadly than intended when handling user-controlled inputs or preparing live API calls.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The invocation criteria are broad enough to match common activities like coding assistance, planning, summarization, and multi-turn chat, which can cause the skill to activate in many contexts beyond narrowly scoped PoYo API integration. Over-broad triggering increases the risk of unnecessary external model routing, data exposure to third-party infrastructure, or use in situations where safer/local handling would be more appropriate.

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 · references/api.md (reported line 55)May include surrounding context.

Basic Messages Example

bash
curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: YOUR_API_KEY" \
  --header "anthropic-version: 2023-06-01" \

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/submit_claude_sonnet_5_messages.sh (reported line 13)May include surrounding context.

sh
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script performs an HTTP POST to an external API and includes both the contents of the provided payload file and an API key in request headers. There is no confirmation prompt, logging/print statement, or explanatory comment/docstring in the file warning the user that local file contents will be sent to a remote service using credentials from the environment.

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 3)May include surrounding context.

md
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \

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 · references/api.md (reported line 5)May include surrounding context.

md
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \

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 · references/api.md (reported line 56)May include surrounding context.

md
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \

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 · references/api.md (reported line 77)May include surrounding context.

md
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \

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 · references/api.md (reported line 115)May include surrounding context.

md
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \

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/submit_claude_sonnet_5_messages.sh (reported line 14)May include surrounding context.

sh
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/v1/messages" \
  --header "x-api-key: ${POYO_API_KEY}" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \