specs-kit-code-cleanup
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to automatically discover and execute project-specific development tools (such as formatters, linters, and test runners) based on configuration files like
package.json,pyproject.toml, Maven, and Gradle plugins. This involves executing shell commands derived from the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill parses project task files and source code, creating an attack surface where instructions embedded in code comments or task descriptions could influence agent behavior.
- Ingestion points: Reads content from
TASK-XXX.md,TASK-XXX--review.md, and various project source files. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when reading these files.
- Capability inventory: The skill possesses the ability to execute shell commands (via project tools and grep) and write to the file system (to update task statuses and clean code).
- Sanitization: There is no evidence of sanitization or filtering applied to the content extracted from external files before processing.
Audit Metadata