skills/44madfire/orca/orca-cli/Gen Agent Trust Hub

orca-cli

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the orca CLI (or its variants orca-ide and orca-dev) to perform system operations like worktree management, terminal control, and browser automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes a dynamic instruction loading pattern where it fetches a version-matched guide from the output of the ORCA skills get orca-cli command. 1. Ingestion points: The agent is instructed to read and follow the output of the orca command at runtime within SKILL.md. 2. Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the fetched guide. 3. Capability inventory: The skill has broad capabilities including terminal access, browser control, and filesystem operations through the CLI. 4. Sanitization: Absent; the output is used as a direct guide for agent behavior.
  • [DYNAMIC_EXECUTION]: The skill implements dynamic instruction assembly by deferring the discovery of specific command syntax and flags to runtime execution of the CLI's help and guide commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:43 PM
Security Audit — agent-trust-hub — orca-cli