skills/rlaope/oh-my-hermes/omh-wiki/Gen Agent Trust Hub

omh-wiki

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several external GitHub repositories in references/wiki-ecosystem.md as ecosystem candidates for evaluation, such as github.com/mudrii/hermes-agent-docs and github.com/dannyshmueli/obsidian-hermes-console.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input regarding audience scale, knowledge types, and destination stores to design wiki blueprints, creating a surface for indirect instructions.
  • Ingestion points: Data provided by the user during the design interview phase in SKILL.md.
  • Boundary markers: Explicit instructions to record missing facts and handle staleness warnings.
  • Capability inventory: Uses omh runtime shell commands for session tracking and references handoffs to external connectors.
  • Sanitization: Uses structured markdown templates and defined blueprint fields (wiki_blueprint/v1) to constrain data capture.- [COMMAND_EXECUTION]: The skill utilizes platform-native shell commands including omh runtime record and omh runtime todo show to manage and retrieve session-specific task data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:34 PM
Security Audit — agent-trust-hub — omh-wiki