The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads terminal output from experiment runs, which is an external data source that could contain malicious instructions designed to influence the agent.
Ingestion points: terminal logs retrieved via orx logs as described in SKILL.md.
Boundary markers: none specified for the log content.
Capability inventory: log reading, metric analysis, and report generation.
Sanitization: no explicit sanitization of log content is described.
[COMMAND_EXECUTION]: The skill executes the orx command to retrieve persisted results, which is consistent with its intended use case and represents the primary functionality provided by the vendor.

orx-evidence