Revibe Codes

Security checks across static analysis, malware telemetry, and agentic risk

Overview

Revibe Codes appears aligned with its advertised repo-analysis purpose, but it sends repository data to Revibe and saves reusable local context, so use it only for repositories you are comfortable sharing.

Before installing, make sure you are allowed to share the target repository with Revibe, especially for private or proprietary code. Review Revibe’s privacy/retention terms, protect the REVIBE_API_KEY, and only enable the optional curl allowed-tools shortcut if you are comfortable reducing prompts for Revibe API calls.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI03: Identity and Privilege Abuse
Low
What this means

Anyone with the key may be able to use the user’s Revibe account or quota.

Why it was flagged

The skill uses a service API key, which is expected for Revibe access, but it is still a credential users should protect and scope appropriately.

Skill content
**REVIBE_API_KEY** (required): API key for authentication... Sent as `X-Revibe-Key` header.
Recommendation

Use a dedicated Revibe API key if possible, keep it out of logs and shared files, and revoke it if no longer needed.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Repository contents may leave the local environment and be stored by Revibe’s infrastructure.

Why it was flagged

The external data flow and cloud storage of repository source code are clearly disclosed and purpose-aligned, but they are sensitive for private or proprietary repositories.

Skill content
This skill sends your repository's GitHub URL to revibe.codes for analysis. Source code is stored securely in Google Cloud Storage...
Recommendation

Review Revibe’s privacy and retention terms before using this on private, proprietary, regulated, or customer-owned code.

#
ASI06: Memory and Context Poisoning
Low
What this means

Future tasks may rely on the saved agent_context.json, which could include sensitive architectural details or stale/incorrect assumptions.

Why it was flagged

The skill creates persistent local context that future agent actions or other skills may reuse.

Skill content
Always save the agent context file after showing the summary... This file gives the agent (and other skills) structured codebase understanding for future tasks.
Recommendation

Review or delete agent_context.json when working with sensitive repositories or when the analysis becomes outdated.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

If enabled, future Revibe API calls may require less interactive confirmation.

Why it was flagged

This is an optional, disclosed tool-permission relaxation scoped to Revibe curl calls; it is useful for the workflow but lowers approval friction.

Skill content
To reduce permission prompts, you can optionally add `Bash(curl *revibe.codes*)` to your allowed tools via `/allowed-tools`.
Recommendation

Only add the allowed-tools rule if you are comfortable with repeated Revibe network calls, and remove it when no longer needed.