hermes-rhythm

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSPERSISTENCE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates for executing shell commands using the hermes CLI to create scheduled jobs and manage session states.
  • Evidence: hermes -p <chief-profile> cron create ... and hermes plugins install hermes-session-reset-policy found in references/templates/cron-jobs.md and references/decisions-and-reset.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external workspace files and task registries which may contain content from untrusted sources.
  • Ingestion points: registry.md, dossier README files, and the output of hermes kanban list (specified in references/commitments-registry.md and references/rituals.md).
  • Boundary markers: No explicit XML-style delimiters or 'ignore' instructions are included in the prompt templates to isolate untrusted data.
  • Capability inventory: The skill has the capability to create persistent cron jobs and install plugins.
  • Sanitization: No specific sanitization or filtering logic is provided for the content read from files before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill references and recommends the installation of external plugins and checking for updates from well-known project repositories.
  • Evidence: Reference to official releases on GitHub and instructions to install the hermes-session-reset-policy plugin.
  • [PERSISTENCE]: The skill utilizes the agent's native cron functionality to schedule recurring tasks that run in the background across sessions.
  • Evidence: Multiple hermes cron create commands are provided to set up daily and weekly automated routines in references/templates/cron-jobs.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 09:23 AM