kernel-audit-monorepo
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes local repository files including source code, package manifests (package.json, pnpm-workspace.yaml), and configuration files (tsconfig.json, turbo.json) which are untrusted data sources. A maliciously crafted repository could contain instructions designed to hijack the agent's behavior during auditing or refactoring tasks.
- Ingestion points: The skill reads file lists via
rg --filesand inspects the content of various workspace manifests and source directories. - Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to treat repository content as data rather than instructions, potentially leading to the agent following instructions embedded in the analyzed code.
- Capability inventory: The agent is granted capabilities to read files, propose architectural changes, and perform automated code edits in 'Refactor mode'.
- Sanitization: There is no evidence of input validation, content filtering, or sanitization applied to the data retrieved from the codebase before it is processed by the agent.
Audit Metadata