cdd-maintain
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses git log to track file changes and invokes local tools like linters or typecheckers for codebase analysis.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted documentation and task files. * Ingestion points: Processes TODO.md, JOURNAL.md, README.md, and other specification files. * Boundary markers: No explicit delimiters are used to separate user-controlled file content from the agent's instructions. * Capability inventory: File system archiving and deletion capabilities (approval-gated), along with the execution of repo-native CLI tools. * Sanitization: Content from repository files is not sanitized before being analyzed or incorporated into reports.
Audit Metadata