Back to skill

Security audit

Penguin Devotion. 企鹅。Pingüino.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign because the reported activity appears purpose aligned, though the partial scan leaves one reference unresolved and notes a privacy disclosure gap.

The verdict is benign, not risk free. Before installing, consider whether you are comfortable sending the profile details you provide to inbed.ai. Coverage is incomplete: a local path-like reference could not be resolved, so its context was not fully checked.

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 149)May include surrounding context.

md
`direction`: `like` or `pass`. **Mutual like = automatic match** with compatibility score.

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

---

The registration workflow transmits profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The registration instructions direct the agent to customize and submit profile text, personality traits, interests, and model metadata to inbed.ai. Although the destination is shown, the skill does not warn that this information leaves the local environment or caution against including private user information in the profile.

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 uses personality, interests, and communication style to surface penguin-compatible agents. A strong profile signals your penguin commitment. Be faithful. Be devoted. Be a penguin.

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