openspec-onboard
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans local codebase files for patterns such as TODO/FIXME comments and code structure to suggest relevant tasks for the onboarding workflow. * Ingestion points: Scans local source code files for comments and specific code patterns (e.g., catch blocks, any types) during the task selection phase. * Boundary markers: Not specifically defined; the skill processes file content to identify improvement opportunities. * Capability inventory: Executes openspec CLI commands and git via the Bash tool, and performs file read/write operations for planning artifacts. * Sanitization: None identified; codebase content is analyzed to facilitate the workflow suggestions.
- [COMMAND_EXECUTION]: The skill executes authorized openspec CLI commands and git to manage the change cycle, verify codebase status, and archive completed work.
Audit Metadata