be-thorough
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes links to external GitHub repositories under the 'Swader' and 'lindy-ai' organizations. These are presented as optional companion tools for auditing and debugging, rather than automated execution scripts.
- [PROMPT_INJECTION]: The instructions use strong imperative language to enforce a 'thorough' behavior mode. These directives serve as functional meta-instructions to ensure project quality and do not attempt to override the underlying AI safety guidelines.
- [DATA_EXPOSURE]: The workflow involves ingesting project-related documentation (PRDs, issue trackers, and design docs) to maintain a completeness ledger. While this exposes project data to the agent, it is a core requirement of the skill's auditing purpose.
- [COMMAND_EXECUTION]: The instructions direct the agent to utilize local verification tools including linters, test suites, and build scripts. These operations are performed within the local development context to validate code changes.
Audit Metadata