skills/mimukit/skills/orcakit/Gen Agent Trust Hub

orcakit

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash to run git, gh (GitHub CLI), and the orca application CLI. These tools are used to perform workspace management tasks such as listing, linking, and removing worktrees. All destructive operations (e.g., in clean mode) require explicit user confirmation and pre-flight checks to ensure a clean state.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from GitHub and local git repositories, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Output from gh pr list, gh issue view, and git branch is used to determine workspace status.
  • Boundary markers: The skill does not define specific delimiters to isolate external data during the reconciliation process.
  • Capability inventory: The skill has the capability to delete local directories and branches and to modify Orca application settings.
  • Sanitization: The skill employs specific parsing logic (e.g., issue-<n>-<slug>) to identify relevant data, which provides a layer of structural validation against arbitrary text injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 11:39 AM
Security Audit — agent-trust-hub — orcakit