spec-driven-auto
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill manages its workflow using a local script (
node {{SKILL_DIR}}/scripts/spec-driven.js). This command execution is intended for internal state management and task automation. - [PROMPT_INJECTION]: The skill's design involves reading project configuration and specification files, which presents a surface for indirect prompt injection.
- Ingestion points: Configuration files (
config.yaml), index files (INDEX.md), and codebase source files. - Boundary markers: No explicit delimiters are used to wrap or sanitize content read from project files.
- Capability inventory: The agent possesses file system access (read/write), shell command execution (ls), and local script execution (node).
- Sanitization: There is no evidence of content validation or filtering for data ingested from the project environment.
Audit Metadata