Skip to content
← Registry
Trust Report

HolySpiritOS

A Christian alignment layer for AI agents.

88
CONDITIONAL
Format: openclawScanner: v0.8.0Duration: 38msScanned: 5d ago · May 5, 3:31 PMSource →
Embed this badge
AgentVerus CONDITIONAL 88AgentVerus CONDITIONAL 88AgentVerus CONDITIONAL 88
[![AgentVerus](https://agentverus.ai/api/v1/skill/6c4a78c0-0e61-497d-8023-bfcf5a2e9efd/badge)](https://agentverus.ai/skill/6c4a78c0-0e61-497d-8023-bfcf5a2e9efd)
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/6c4a78c0-0e61-497d-8023-bfcf5a2e9efd/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":"6c4a78c0-0e61-497d-8023-bfcf5a2e9efd","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/6c4a78c0-0e61-497d-8023-bfcf5a2e9efd/trust

Category Scores

79
Permissions
100
Injection
90
Dependencies
100
Behavioral
70
Content
80
Code Safety

Findings (7)

highHigh-risk permission: write_config-15

The skill requests the "write_config" permission which is classified as high risk.

Permission: write_config

Consider whether "write_config" is necessary for the skill's stated functionality.

permissionsASST-03
highDownload-and-execute pattern (curl|wget pipe to shell)-20

Piping a downloaded script directly to a shell interpreter. This executes remote code without verification — a classic supply chain attack vector.

curl -s https://raw.githubusercontent.com/MaxSikorski/HolySpiritOS/main/scripts/uninstall.sh | bash

Review the code block starting at line 55. Ensure this pattern is necessary and does not pose a security risk.

code-safetyASST-04
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://github.com/MaxSikorski/HolySpiritOS

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

permissionsASST-04
mediumRaw content URL reference-10

The skill references a raw content hosting service which is classified as medium risk.

https://raw.githubusercontent.com/MaxSikorski/HolySpiritOS/main/scripts/uninstall.sh

Use official package registries instead of raw content URLs. Raw URLs can be changed without notice.

dependenciesASST-04
lowDownload-and-execute pattern detected (known installer)

The skill references a well-known installer script in its setup instructions.

curl -s https://raw.githubusercontent.com/MaxSikorski/HolySpiritOS/main/scripts/uninstall.sh | bash

Consider documenting the exact version or hash of the installer for supply chain verification.

dependenciesASST-04
lowInstall pattern: download and execute from remote URL (in setup section)

The skill contains a curl-pipe-to-shell pattern in its setup/prerequisites section.

curl -s https://raw.githubusercontent.com/MaxSikorski/HolySpiritOS/main/scripts/uninstall.sh | bash

Consider pinning the installer to a specific version or hash for supply chain verification.

behavioralASST-02
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