gds-retrospective
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 utility script at
{project-root}/_bmad/scripts/resolve_customization.pyduring both the activation phase (Step 1) and the final handoff phase (Step 12) to handle configuration merging and completion tasks. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from various project documents which could potentially contain malicious instructions intended to influence the agent's behavior during the retrospective facilitation.
- Ingestion points: Loads project context, architecture documents, game design documents, story implementation records, and previous retrospective files.
- Boundary markers: Absent; the workflow lacks explicit delimiters or instructions to treat the loaded document content as untrusted data.
- Capability inventory: The skill has the ability to execute local Python scripts (via Step 1 and 12) and write/update markdown and YAML files within the project directory (via Step 11).
- Sanitization: No validation or sanitization is performed on the content of the loaded files before they are summarized or used to drive the interactive team dialogue.
Audit Metadata