skills/houlemon0130/orca/orca-cli/Gen Agent Trust Hub

orca-cli

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill resolves the executable path for the Orca CLI dynamically using environment variables like ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT, or by inspecting the operating system context.
  • [COMMAND_EXECUTION]: The skill fetches its primary instruction set at runtime by executing ORCA skills get orca-cli, ensuring compatibility with the specific version of the binary in use.
  • [PROMPT_INJECTION]: The skill's reliance on instructions fetched from a local command output creates a surface for indirect prompt injection. Ingestion points: Command output from ORCA skills get orca-cli. Boundary markers: No specific markers are provided to the agent to delimit the dynamic instructions. Capability inventory: Full control over Orca worktrees, terminal interactions, and the embedded browser. Sanitization: No sanitization process for the command output is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 12:53 PM
Security Audit — agent-trust-hub — orca-cli