openspec-onboard
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands using the
openspecCLI (e.g.,openspec status,openspec new,openspec archive) andgit(e.g.,git log) to facilitate the onboarding process. - [PROMPT_INJECTION]: In Phase 2, the skill scans the local codebase for patterns like
TODOorFIXME. This ingestion of untrusted local file content serves as an entry point for indirect prompt injection, where malicious text in the source code could influence the agent's task suggestions or narration. - Ingestion points: Reads local code files searching for comments and patterns as defined in SKILL.md.
- Boundary markers: None explicitly defined for the codebase scanning logic.
- Capability inventory: Executes CLI commands (
openspec,git), creates directories (mkdir), and writes to the filesystem (Phase 9 implementation). - Sanitization: No specific sanitization or filtering of codebase content is mentioned before processing.
Audit Metadata