openspec-onboard

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies potential tasks by scanning the local codebase for patterns such as 'TODO', 'FIXME', and 'any' types in TypeScript. While this involves ingesting untrusted data from the user's environment, the data is used solely to provide human-readable task suggestions within a guided workflow and does not target agent control flow.
  • [COMMAND_EXECUTION]: The skill executes local commands including openspec, git log, and environment checks (--version). These operations are scoped to the primary purpose of the skill and utilize appropriate automation flags (e.g., --yes) to facilitate non-interactive execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:17 PM
Security Audit — agent-trust-hub — openspec-onboard