product-specify
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local setup scripts including
scripts/bash/setup-product-specify.shandscripts/powershell/setup-product-specify.ps1. These scripts perform environment checks, directory creation, and local path resolution for Product Decision Records (PDRs). They rely on internal project structure and local dependencies from the same author. - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where instructions hidden in the codebase could influence AI behavior.
- Ingestion points: In Phase 2, the skill reads content from
README.md,AGENTS.md,CONTRIBUTING.md, and{REPO_ROOT}/docs/adlc/memory/constitution.mdto extract product drivers. - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions when parsing these local files.
- Capability inventory: The skill can create and write files to the
.adlc/drafts/pdr/directory and regenerate indices, which are later used for project documentation. - Sanitization: No specific sanitization or filtering of the extracted text is mentioned before it is processed by the model to generate the PDR draft.
Audit Metadata