gds-performance-test
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
{project-root}/_bmad/scripts/resolve_customization.pyduring both the activation and completion phases. This script is used to merge configuration files from the skill root and the project's customization directories. - [INDIRECT_PROMPT_INJECTION]: The workflow involves reading and processing external data from the project directory which could potentially contain malicious instructions.
- Ingestion points: Reads customization files (
{skill-name}.toml,{skill-name}.user.toml), project configuration (config.yaml), and any files specified in thepersistent_factslist (SKILL.md, Steps 1, 3, and 4). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when processing the content of these external files.
- Capability inventory: The skill has the capability to read project files, write to an output folder, and execute the local
resolve_customization.pyscript. - Sanitization: There is no evidence of sanitization or validation of the input data extracted from the configuration and project files before it is used to influence the agent's workflow.
Audit Metadata