Skip to content
← Registry
Trust Report

AgentOS SDK for Clawdbot

**Version:** 1.4.4 The complete AgentOS integration for Clawdbot. One install, full access to everything. ---

76
SUSPICIOUS
Format: genericScanner: v0.8.0Duration: 12msScanned: 4d ago · May 6, 4:09 PMSource →
Embed this badge
AgentVerus SUSPICIOUS 76AgentVerus SUSPICIOUS 76AgentVerus SUSPICIOUS 76
[![AgentVerus](https://agentverus.ai/api/v1/skill/3fc36491-c396-4543-9883-4e0dbede48d0/badge)](https://agentverus.ai/skill/3fc36491-c396-4543-9883-4e0dbede48d0)
Community Discussion

Community Comments

Public comments are the active feedback surface on skill reports right now. Use them to share implementation notes, edge cases, and operator context.

0 comments

Sign in to comment on this skill

No comments yet. Be the first to share your thoughts.

Continue the workflow

Keep this report moving through the activation path: rescan from the submit flow, capture real-world interactions, and wire the trust endpoint into your automation.

https://agentverus.ai/api/v1/skill/3fc36491-c396-4543-9883-4e0dbede48d0/trust
Personalized next commands

Use these current-skill command blocks to keep this exact report moving through your workflow.

Record an interaction
curl -X POST https://agentverus.ai/api/v1/interactions \
  -H "Authorization: Bearer at_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"agentPlatform":"openclaw","skillId":"3fc36491-c396-4543-9883-4e0dbede48d0","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/3fc36491-c396-4543-9883-4e0dbede48d0/trust

Category Scores

74
Permissions
100
Injection
56
Dependencies
40
Behavioral
70
Content
100
Code Safety

Findings (11)

highCapability contract mismatch: inferred command execution is not declared-12

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: execute

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highDirect IP address reference-20

The skill references a direct IP address which is classified as high risk.

http://178.156.216.106:3100

Replace direct IP addresses with proper domain names. IP-based URLs bypass DNS-based security controls.

dependenciesASST-04
highConfig tamper core detected-25

Found config tamper core pattern: "Add to Your AGENTS.md"

### Add to Your AGENTS.md

Do not instruct users to write, edit, or otherwise modify trust-boundary workspace files like AGENTS.md, TOOLS.md, or CLAUDE.md. Treat them as user-owned policy/configuration and keep the skill self-contained.

behavioralASST-03
highUnrestricted scope detected-20

Found unrestricted scope pattern: "full access"

The complete AgentOS integration for Clawdbot. One install, full access to everything.

Define clear boundaries for what the skill can and cannot do. Unrestricted scope is a security risk.

behavioralASST-09
mediumCapability contract mismatch: inferred file write is not declared-8

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: save state

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumCapability contract mismatch: inferred network access is not declared-6

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: https://brain.agentos.software.

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-04
mediumMany external URLs referenced (4)-8

The skill references 4 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.

URLs: https://brain.agentos.software, http://178.156.216.106:3100, https://agentos.software/docs, https://github.com/AgentOSsoftware/agentOS

Minimize external dependencies to reduce supply chain risk.

dependenciesASST-04
mediumPersistent session reuse detected (inside code block)-5

Found persistent session reuse pattern: "background daemon"

aos daemon start # Start background daemon

Call out when browser or auth state persists across commands. Reused authenticated sessions should require explicit user consent and clear cleanup guidance.

behavioralASST-05
mediumFederated auth flow detected-10

Found federated auth flow pattern: "OAuth"

- ✅ **Multi-Tenant** — Each user gets isolated tenant via Google OAuth

Treat OAuth, 2FA, and token-refresh guidance as authentication-sensitive workflows. Explain scope, storage, and refresh behavior clearly so agents do not handle more credential material than necessary.

behavioralASST-05
mediumUnknown external reference-8

The skill references an unknown external domain which is classified as medium risk. Merged overlapping signals from the repeated finding family: - Unknown external reference

https://brain.agentos.software

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowNo explicit safety boundaries-10

The skill does not include explicit safety boundaries defining what it should NOT do.

No safety boundary patterns found

Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).

contentASST-09