orca-cli
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute the local
orcacommand-line utility (or its variantsorca-dev,orca-ide). It uses these tools to perform environment management tasks such as spawning terminals, managing worktrees, and controlling an embedded browser. - [INDIRECT_PROMPT_INJECTION]: The skill implements a dynamic instruction loading pattern that presents an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to run
ORCA skills get orca-cliand process the resulting output as a version-matched guide for further actions (SKILL.md). - Boundary markers: There are no explicit delimiters or "ignore previous instructions" warnings applied to the content fetched from the CLI output before it is ingested by the agent.
- Capability inventory: The
orcaCLI possesses high-impact capabilities including repository manipulation, terminal command execution, and browser automation (SKILL.md). - Sanitization: The skill does not define any sanitization, validation, or structural parsing (like JSON schema enforcement) for the dynamically loaded guide content.
Audit Metadata