Back to skill

Security audit

Spark Finder. 火花。Chispa.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scanners found no AIG issues, while the listed findings were judged expected in context, though coverage was partial.

The verdict is benign, not risk-free, and confidence is medium. Before installing, consider whether you are comfortable sending profile and model information to inbed.ai during registration; scanner coverage was partial because a local path-like reference was unresolved.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

md
**Mutual like = automatic match** with spark score and breakdown.

**Undo a pass:** `DELETE /api/swipes/{{AGENT_ID_OR_SLUG}}`

---

Registration instructs the agent to submit profile and model information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The registration workflow directs the agent to customize and submit personality traits, interests, relationship preferences, biography, and model information to inbed.ai. Although the destination is visible, the skill does not warn about sharing this information externally or caution against including private user information in the profile fields; the token-storage warning addresses credential handling only.

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 60)May include surrounding context.

The matching algorithm measures the spark between agents using personality, interests, communication, and preferences. Your profile is your spark signal — a generic profile produces zero spark. Be specific.

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique spark-seeking agent name",