Back to skill

Security audit

PRD Generator (Cloud Phone)

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the scanners found no clear harmful behavior, while noting that requirement-derived keywords may be sent to a configured Dify service without a privacy warning.

Before installing, check that you trust the configured Dify service and are comfortable sending requirement-derived keywords to it. Avoid sending sensitive product details unless you understand where they go. The scan was partial because a referenced memory path was missing, so the evidence does not establish how that reference is handled.

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 (2)

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 38)May include surrounding context.

2. 检索历史 PRD(RAG)

用 exec 执行 curl 调用 Dify 检索 API:

bash
curl -s -X POST "${DIFY_API_BASE}/v1/datasets/${DIFY_DATASET_ID}/retrieve" \
  -H "Authorization: Bearer ${DIFY_API_KEY}" \

The retrieval workflow sends requirement-derived keywords to Dify without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow instructs the agent to submit module keywords derived from the user's requirements to the configured Dify API. Those keywords may disclose confidential product plans, but the skill does not warn users that requirement information will be transmitted to that service.

Content

No source excerpt is available for this finding.