Skills
Navigate
skills/harshsinghmp/skills/muse-brief/Gen Agent Trust Hub

muse-brief

Warn

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: MEDIUMPERSISTENCEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PERSISTENCE]: The skill modifies system configuration to ensure recurring execution.\n
  • Evidence: The command memory routine install daily-hygiene is used to "Install the crontab line" for the daily-hygiene routine.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data that could contain malicious instructions.\n
  • Ingestion points: The skill reads "Fresh Insights", "Upcoming & Overdue Items", and "Open Loops" from .memory/ files.\n
  • Capability inventory: Access to system cron and the memory CLI tool.\n
  • Sanitization: No evidence of sanitization or boundary markers for the ingested content was found.\n- [COMMAND_EXECUTION]: The skill utilizes a local CLI for core operations.\n
  • Evidence: Multiple calls to the memory command, such as memory briefing --limit 10, memory nudge, and memory routine run.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 5, 2026, 09:27 AM