beyond-code-verify
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically identifies and executes project-specific tooling commands for linting, typechecking, building, and running tests. These commands are derived from the project environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of
git diffoutputs and project documentation (spec.md,plan.md) to be processed by a subagent for auditing. This represents a surface where malicious instructions could be embedded in code comments or requirements documents to influence the agent's behavior. - Ingestion points: Reads
git diff,.beyond-code/<slug>/spec.md, and.beyond-code/<slug>/plan.mdin Stage 1. - Boundary markers: None identified. The content is passed to the subagent as part of the audit prompt.
- Capability inventory: The skill has the ability to execute shell commands (
lint,test,ls) and perform file system operations (moving directories for archiving). - Sanitization: No escaping or validation is performed on the ingested diff or documentation content before it is processed.
Audit Metadata