Back to skill

Security audit

phishnoo-awareness-sandbox

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with high confidence: its only contextualized finding is an external service address that appears consistent with the stated sandbox purpose.

The verdict is benign with high confidence, and the scan covered the single reported component. Before installing, consider whether you are comfortable with a skill that connects to the named external sandbox service; benign does not mean risk-free.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

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 30)May include surrounding context.

md
Use this skill when the user asks to inspect the Phishnoo sandbox or file a synthetic example report. Configure `PHISHNOO_SANDBOX_KEY` through the client's secret settings and send it only as `Authorization: Bearer <key>` to `https://api.phishnoo.nl`. Never include it in URLs, command arguments, reports, or output.

Connect over Streamable HTTP at `https://api.phishnoo.nl/mcp`. Use `get_me`, `get_scores`, `get_campaigns`, `get_progress`, and `get_threats` to read sandbox data. Use `report_threat` only when the user requests a write. Send a synthetic title and optional example URL without credentials, query, or fragment. Never send employee records, actual messages, or live customer data.

REST fallback: GET /v1/me, /v1/scores, /v1/campaigns, /v1/progress, /v1/threats; POST /v1/threats with JSON. See https://api.phishnoo.nl/docs.

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 32)May include surrounding context.

md
Connect over Streamable HTTP at `https://api.phishnoo.nl/mcp`. Use `get_me`, `get_scores`, `get_campaigns`, `get_progress`, and `get_threats` to read sandbox data. Use `report_threat` only when the user requests a write. Send a synthetic title and optional example URL without credentials, query, or fragment. Never send employee records, actual messages, or live customer data.

REST fallback: GET /v1/me, /v1/scores, /v1/campaigns, /v1/progress, /v1/threats; POST /v1/threats with JSON. See https://api.phishnoo.nl/docs.