re0-release
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several local tools to perform repository audits and git management, including
sip,shower,factchk,mandela,ssotize,re0, andre0-git. These tools are used to verify consistency and prepare the release state. - [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data from the repository which defines an attack surface for indirect prompt injection.
- Ingestion points: Processes the 'pending diff' and the
AGENTS.mdfile (Step 1). - Boundary markers: No specific delimiters or safety instructions are defined for processing these inputs.
- Capability inventory: Performs filesystem writes (
package.json, release notes), executes local CLI tools, and performs network-reaching git operations (git push). - Sanitization: The skill relies on manual human checkpoints (Workflow steps 6 and 8) where explicit confirmation is requested before performing commits or pushing code to a remote server.
Audit Metadata