feature-flag-management
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to perform repository scanning using commands likegrep,awk, andsortto identify and manage feature flag instances within the source code. - [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its operational workflow:
- Ingestion points: Analyzes local source code files (via
GrepandRead) and can fetch external documentation or data viaWebFetch. - Boundary markers: No explicit markers or "ignore" instructions are defined to separate ingested data from agent instructions.
- Capability inventory: The skill has access to
Bash,Write, andEdit, allowing it to modify files based on its analysis of potentially untrusted code content. - Sanitization: No validation or escaping of extracted content is specified before the data is used to influence agent decisions or file modifications.
Audit Metadata