doc-bdd-autopilot
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill orchestrates a series of local Python scripts and shell utilities (such as ls, mkdir, and grep) to automate the documentation lifecycle. These commands are used for file discovery, directory creation, and running validation suites within the project repository.
- [SAFE]: The skill does not perform any external network operations, credential harvesting, or unauthorized privilege escalation. Its operations are strictly confined to local file management and documentation processing according to the specified SSD workflow.
- [SAFE]: Indirect Prompt Injection Surface evaluation. 1. Ingestion points: Data enters the agent context from requirements files located in docs/03_EARS/ (referenced in SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to isolate the content of processed EARS statements. 3. Capability inventory: The skill has the capability to write files to docs/04_BDD/ and execute local scripts via python (detailed in Phase 3 and Phase 4 sections). 4. Sanitization: The skill implements quality gates via doc-ears-validator and doc-bdd-validator to ensure generated content meets structural and compliance standards.
Audit Metadata