The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/flag_debt_scanner.py utilizes subprocess.run to execute local git commands for determining the introduction date of feature flags. The implementation uses a list-based argument structure which correctly handles arguments without shell interpolation, and identifies flags using a restrictive regular expression ([\w.\-:]+), effectively preventing command injection.- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes local source code and documentation to audit feature flags. While this constitutes an external data ingestion surface, the risk is mitigated by the use of static analysis logic within local scripts and the absence of any path where data-derived content is executed as instructions. The tools facilitate a structured review process rather than automated decision-making on untrusted inputs.

feature-flags-architect