spec-driven-simple-task
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is authorized to perform tasks that include editing local project files and running shell commands directly as part of its 'Execute the task' step.- [PROMPT_INJECTION]: The skill reads external data from the .spec-driven/ directory, including configuration and specification files, to use as context for tasks. This creates a surface for indirect prompt injection. Ingestion points: Reads .spec-driven/config.yaml and .spec-driven/specs/INDEX.md (SKILL.md). Boundary markers: Absent. Capability inventory: File editing and shell command execution (SKILL.md). Sanitization: Absent.
Audit Metadata