codeguard-groovy
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (bash -c) combined with find and xargs to locate and process Groovy files. These commands are hardcoded in the skill's instructions and limited to specific file extensions, which reduces risk but grants the agent shell execution capabilities in the local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external Groovy files within a project workspace, which creates a vulnerability surface.
- Ingestion points: The skill targets all files with the .groovy extension within the project workspace during linting and fixing steps (SKILL.md, Step 4).
- Boundary markers: The instructions do not define specific delimiters or warnings to the agent to ignore potentially malicious instructions embedded in the source code it processes.
- Capability inventory: The skill has the ability to execute shell commands and modify local files (npm-groovy-lint --fix) as documented in references/tooling/toolchain.md.
- Sanitization: No evidence of content sanitization or validation of the Groovy files' contents is mentioned before they are analyzed by the agent or passed to tools.
Audit Metadata