orca-cli
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using vendor-provided binaries (h0x, h0x-dev, or orca) to manage h0x-ADE resources including worktrees, terminals, and the internal browser.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the dynamic loading of instructions via the command output of 'ORCA skills get orca-cli'. This architecture creates a potential surface for prompt injection if the tool's output is manipulated.
- Ingestion points: The output of the command 'ORCA skills get orca-cli' as specified in the session resolution logic of SKILL.md.
- Boundary markers: No specific boundary markers or instruction-ignoring delimiters are provided to the agent for processing the fetched guide.
- Capability inventory: The skill enables management of terminals, worktree comments, and browser automation via the h0x CLI as described in the frontmatter and body.
- Sanitization: There is no evidence of sanitization, validation, or schema enforcement for the content retrieved from the CLI guide.
Audit Metadata