The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the vendor's own CLI tool, specifically prime env install and prime eval run. These commands are used to verify the functionality of environment modules being reviewed.
[INDIRECT_PROMPT_INJECTION]: The skill represents a data ingestion surface as it audits external environments sourced from local paths or a remote Hub.
Ingestion points: Environment modules are loaded from ./environments/ or pulled from a remote Hub via prime env pull.
Boundary markers: No explicit instructions or delimiters are provided to the agent to treat the environment code as untrusted data during the analysis phase.
Capability inventory: The skill has the capability to execute code from the environment through the prime eval run command.
Sanitization: There is no automated sanitization of the environment code before it is analyzed or executed.

review-environments