The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill explicitly instructs the agent to "re-run it with escalated permissions" if a connection is blocked by a sandbox. This encourages the agent to bypass security constraints using administrative privileges.
[DYNAMIC_EXECUTION]: The command ORCA skills get orca-cli is used to fetch and load a version-matched guide at runtime. This dynamically alters the agent's instructions and behavior based on output from an external executable.
[INDIRECT_PROMPT_INJECTION]: The skill incorporates external content into the agent's context through the skills get command, creating a surface for indirect prompt injection if the fetched guide contains malicious instructions.
Ingestion points: Output from the ORCA skills get orca-cli command in SKILL.md.
Boundary markers: No delimiters or sanitization instructions are provided for the content returned by the CLI.
Capability inventory: The skill has the ability to execute shell commands, manage filesystems, and escalate permissions.
Sanitization: None present; the agent is instructed to use the guide's content for subsequent commands.
[COMMAND_EXECUTION]: The skill facilitates the execution of arbitrary commands via the orca CLI and its variants (orca-dev, orca-ide), including environment-variable-driven command resolution.

orca-cli