ClawHub
Back to skill

Security audit

sofya-research

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: its documented research request to Sofya fits its purpose, with a note that queries are sent to an external service.

Before installing, consider that research queries are sent to Sofya. Avoid including secrets or personal or confidential details in queries.

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 (2)

The workflow sends research queries to Sofya without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to call Sofya's research service and submit the research query through MCP or an HTTP request. Although it documents the service and credit cost, it does not warn that the query and any user-provided context included in it are transmitted to a third party.

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 34)May include surrounding context.

Parameters: query (required), topic (general | news), freshness (day, week, month, year, or YYYY-MM-DD:YYYY-MM-DD), max_sources (5-30, default 20).

bash
curl -s --max-time 120 -X POST https://sofya.co/v1/research \
  -H "Authorization: Bearer $SOFYA_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "how do heat pumps perform in cold climates", "max_sources": 15}'