code-generation
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The helper script
scripts/check-generated.shexecutes shell commands usingbash -lc. These commands are typically repository-specific wrappers likemake generateor direct CLI tool calls. - [DYNAMIC_EXECUTION]: The script
scripts/check-generated.shexecutes an inline Python snippet via a heredoc to process and output the status of the generation task in JSON format. - [INDIRECT_PROMPT_INJECTION]: This skill has a wide ingestion surface, as it is designed to read and analyze various repository artifacts including schemas, query files, and build configurations.
- Ingestion points: The agent reads .proto, SQL, OpenAPI, and template files as inputs for generation (SKILL.md).
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions within these data files.
- Capability inventory: The skill utilizes shell command execution and file system interaction (scripts/check-generated.sh).
- Sanitization: No specific sanitization or validation of the content of the schema/template files is performed before processing.
Audit Metadata