skills/b0d9a/orca/orca-cli/Gen Agent Trust Hub

orca-cli

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute the orca command-line utility. It provides specific logic to select the appropriate binary (orca, orca-ide, or orca-dev) based on environment variables like ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT, as well as the operating system environment.
  • [PROMPT_INJECTION]: The skill's primary function involves interacting with terminals and browser sessions, creating a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the context via Orca-managed terminal outputs and browser content (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are defined in this discovery stub to separate external content from agent instructions.
  • Capability inventory: The agent is granted the ability to execute shell commands, send terminal input, and automate browser actions via the orca executable.
  • Sanitization: No sanitization or filtering logic for data retrieved from external sources is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 10:37 AM
Security Audit — agent-trust-hub — orca-cli