mo-orchestrate-orca

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes external command-line tools including git, gh (GitHub CLI), glab (GitLab CLI), and the orca-cli backend to perform repository management, issue routing, and feature orchestration.
  • [DYNAMIC_EXECUTION]: The bundled mo-posture.sh script dynamically executes diagnostic probes within bash and zsh environments to detect shadowed builtins or malicious aliases. The Orca mechanics also support launching terminal sessions with harness-specific commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as GitHub/GitLab issue descriptions and user-provided intent ledgers. It mitigates these risks through a mandatory redaction protocol that identifies and masks sensitive information (tokens, passwords, private keys) before commits are made.
  • [SAFE]: No malicious patterns were detected. The skill includes defensive measures such as privileged mode shell execution, strict temporary file permissions (umask 077), and comprehensive logging of automated decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 11:11 AM
Security Audit — agent-trust-hub — mo-orchestrate-orca