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

orca-cli

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides specific commands to interact with the Orca CLI (e.g., status, worktree ps, terminal list). It includes environment-based logic to resolve the correct executable (orca, orca-ide, orca-dev), which includes explicit safety warnings to avoid accidental execution of unrelated system binaries such as the GNOME Orca screen reader.
  • [PROMPT_INJECTION]: The skill utilizes a dynamic discovery pattern, instructing the agent to fetch its primary instruction set from a local binary using ORCA skills get orca-cli. This represents an indirect prompt injection surface as the agent is told to follow instructions generated at runtime.
  • Ingestion points: The output of the ORCA skills get orca-cli command is ingested into the agent context (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the output of the guide command (SKILL.md).
  • Capability inventory: The skill allows the agent to execute shell commands via the resolved Orca binary.
  • Sanitization: The skill does not perform sanitization, escaping, or validation of the dynamically loaded content before it is processed as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 11:12 PM
Security Audit — agent-trust-hub — orca-cli