orca-cli

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches its primary instruction set from the output of an external command, which is an untrusted data source. 1. Ingestion points: The agent is instructed to run ORCA skills get orca-cli and treat the output as the "complete, version-matched guide" for the session (SKILL.md). 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing of the tool output. 3. Capability inventory: The agent has the capability to execute shell commands, manage worktrees, control terminals, and operate an embedded browser using the orca binary (SKILL.md). 4. Sanitization: No validation or sanitization is performed on the content returned by the CLI tool before it is used as guidance.
  • [COMMAND_EXECUTION]: The skill instructs the agent to resolve an executable path from environment variables or specific filenames and execute shell commands with user-controlled or tool-suggested arguments (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 05:46 AM