design-doc
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python validation script (
story_contract.py) to verify the syntax and contract compliance of generated design documents. This script is resolved from the repository or an installed skill set (design-to-issues/scripts/). - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from repository files and conversation history to generate output.
- Ingestion points: Conversation history and repository files (architecture, code, tests, schemas, and configuration) are read in the "Ground the design" and "Mine the conversation" workflow steps.
- Boundary markers: The skill does not explicitly define delimiters or specific instructions for the agent to ignore potentially malicious instructions embedded within the ingested source data.
- Capability inventory: The skill invokes a local Python interpreter for validation and performs file-write operations to the
docs/design/directory. - Sanitization: No explicit sanitization or filtering of the repository-sourced content is described before it is synthesized into the final design documents.
Audit Metadata