gds-agent-tech-writer
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script at
{project-root}/_bmad/scripts/resolve_customization.pyduring activation to merge configuration files (SKILL.md). - [INDIRECT_PROMPT_INJECTION]: The
update-standards.mdcomponent allows users to append 'CRITICAL' rules to thedocumentation-standards.mdfile. These rules are subsequently used as high-priority instructions for the agent, creating a risk where malicious input could persistently alter the agent's behavior or safety constraints. - [INDIRECT_PROMPT_INJECTION]: The agent is designed to ingest and analyze untrusted external data, such as
project-context.mdfiles and user-submitted documents for validation. These inputs could contain hidden instructions intended to influence the agent's output or the execution of its writing tasks.
Audit Metadata