add-molab-badge
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
uvx marimofor exporting notebook sessions andgit remotefor repository metadata discovery, which are routine operations for managing marimo-based projects. - [INDIRECT_PROMPT_INJECTION]: The skill processes repository files and user-provided URLs to insert badges into target files, presenting a potential (though standard) surface for processing untrusted data.
- Ingestion points: Processes repository notebook file paths, notebook content headers (checking for
import marimo), and user-supplied URLs. - Boundary markers: No specific boundary markers or "ignore embedded instructions" warnings are defined for the badge insertion process.
- Capability inventory: Capabilities include file modification (in-place editing of READMEs/HTML) and shell command execution (
uvx,git). - Sanitization: No explicit sanitization or validation of input paths is performed beyond verifying the marimo header.
Audit Metadata