openspec-onboard

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several local commands including openspec status, git log, openspec new change, and openspec archive. These are used to manage the project's state and decision history within the intended OpenSpec workflow.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. Ingestion points: The agent scans the local codebase for TODO/FIXME comments and reads file contents in Phase 2 and Phase 3 to suggest tasks. Boundary markers: No delimiters or specific instructions are provided to the agent to treat these external inputs as untrusted or to ignore any embedded instructions. Capability inventory: The skill has the ability to write to the file system and execute shell commands via the openspec and git CLIs. Sanitization: There is no explicit sanitization or validation of the content read from codebase files or git logs before it is used to influence the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 09:05 AM