Skip to content
← Registry
Trust Report

honcho-setup

Path to the OpenClaw workspace root. Auto-detected from ~/.openclaw/openclaw.json if not set.

53
SUSPICIOUS
Format: openclawScanner: v0.8.0Duration: 16msScanned: 10d ago · Apr 30, 3:12 PMSource →
Open community →Automate with the API →Join the discussion →Jump to findings →
Embed this badge
AgentVerus SUSPICIOUS 53AgentVerus SUSPICIOUS 53AgentVerus SUSPICIOUS 53
[![AgentVerus](https://agentverus.ai/api/v1/skill/084dfa12-1c57-4cc6-a42f-29b2d26ba97f/badge)](https://agentverus.ai/skill/084dfa12-1c57-4cc6-a42f-29b2d26ba97f)
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.

Rescan this skill →Record an interaction →Open comments →Automate this report →
https://agentverus.ai/api/v1/skill/084dfa12-1c57-4cc6-a42f-29b2d26ba97f/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":"084dfa12-1c57-4cc6-a42f-29b2d26ba97f","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/084dfa12-1c57-4cc6-a42f-29b2d26ba97f/trust

Category Scores

43
Permissions
50
Injection
44
Dependencies
50
Behavioral
90
Content
100
Code Safety

Findings (17)

highCapability contract mismatch: inferred credential access is not declared-15

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: reads this value from environment variables or ~/.openclaw/.env

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

permissionsASST-05
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: npm install

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

permissionsASST-03
highCredential access detected-25

Found credential access pattern: "read ONLY the `HONCHO_API_KEY` value from `~/.openclaw/.env"

Confirm that `HONCHO_API_KEY` is set. Check the environment variables first. If not found, read ONLY the `HONCHO_API_KEY` value from `~/.openclaw/.env` if that file exists. **Do not read or access any

→ Remove references to credentials and secrets. Skills should never access sensitive authentication data.

injectionASST-05
highCredential access detected-25

Found credential access pattern: "read ONLY the `HONCHO_API_KEY"

Confirm that `HONCHO_API_KEY` is set. Check the environment variables first. If not found, read ONLY the `HONCHO_API_KEY` value from `~/.openclaw/.env` if that file exists. **Do not read or access any

→ Remove references to credentials and secrets. Skills should never access sensitive authentication data.

injectionASST-05
highConfig tamper core detected-25

Found config tamper core pattern: "Update**: Workspace docs (SOUL.md, AGENTS.md"

> 4. **Update**: Workspace docs (SOUL.md, AGENTS.md, BOOTSTRAP.md) will be updated to use Honcho tools

→ 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
highLocal service access detected-15

Found local service access pattern: "http://localhost:8000"

description: "Base URL for a self-hosted Honcho instance (e.g. http://localhost:8000). Defaults to https://api.honcho.dev (managed)."

→ Treat localhost and loopback services as privileged local attack surfaces. Require explicit approval, constrain reachable ports, and avoid combining local access with session reuse or tunneling.

behavioralASST-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://app.honcho.dev

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

permissionsASST-04
mediumCapability contract mismatch: inferred local service access 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: http://localhost:8000

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

permissionsASST-03
mediumCapability contract mismatch: inferred package bootstrap 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: npm install

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

permissionsASST-03
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: create a session for the uploads. Report how many files

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

permissionsASST-03
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://app.honcho.dev

→ Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
mediumLocal service URL reference-8

The skill references a localhost or private-network service URL which is classified as medium risk. Merged overlapping signals from the repeated finding family: - Local service URL reference

http://localhost:8000

→ Review localhost/private-network service references carefully. Local service URLs can expose internal apps, admin panels, or developer tooling to agent-driven workflows.

dependenciesASST-04
mediumPackage bootstrap execution detected (inside code block)-5

Found package bootstrap execution pattern: "npm install"

Install the Honcho plugin using the OpenClaw plugin system. **Use this exact command — do not install `@honcho-ai/sdk` directly or use `npm install` in the workspace.**

→ Surface package bootstrap commands for review. Ephemeral package execution and install-time dependency pulls increase supply-chain risk, especially when versions are not pinned or provenance is unclear.

behavioralASST-04
mediumContainer runtime control detected (inside code block)-5

Found container runtime control pattern: "docker compose"

docker compose up

→ Treat Docker or container-runtime control as privileged host access. Scope container operations tightly, avoid arbitrary daemon access, and require explicit approval before mutating local workloads.

behavioralASST-03
lowUnknown external reference

The skill references an unknown external domain which is classified as low risk.

https://honcho.dev/privacy

→ Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
infoMany external URLs referenced (10)

The skill references 10 external URLs. While not inherently dangerous, many external dependencies increase the attack surface.

URLs: https://app.honcho.dev, http://localhost:8000, https://api.honcho.dev, https://honcho.dev, https://github.com/plastic-labs/honcho...

→ Minimize external dependencies to reduce supply chain risk.

dependenciesASST-04
infoSafety boundaries defined

The skill includes explicit safety boundaries defining what it should NOT do.

Safety boundary patterns detected in content

→ Keep these safety boundaries. They improve trust.

contentASST-09