skills/ganyuanran/aegis/update-aegis/Gen Agent Trust Hub

update-aegis

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (scripts/aegis-update.py and scripts/aegis-doctor.py) to manage software updates and host registration. These commands are integral to the skill's stated purpose of host maintenance.
  • [DATA_EXPOSURE]: The instructions involve reading and writing to configuration files located at ~/.config/aegis/config.toml. This is a standard practice for local tool configuration and persistence within the user's home directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes JSON output from local scripts to determine the state of the system. While this constitutes a data ingestion point, the source is a local script specifically designed for this skill, minimizing the risk of adversarial input.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 05:05 PM
Security Audit — agent-trust-hub — update-aegis