recursive-review-bundle
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts located within the repository structure, specifically
./.recursive/scripts/recursive-review-bundle.pyand./.recursive/scripts/recursive-review-bundle.ps1, to perform its core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for ingesting untrusted data as it is designed to read and bundle repository artifacts. Ingestion points: The skill processes files specified via the
--artifact-pathand--upstream-artifactarguments. Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the skill documentation. Capability inventory: The skill utilizes script execution capabilities to process files. Sanitization: The instructions do not define any validation or filtering mechanisms for the data contained within the processed artifacts.
Audit Metadata