Security Guidance plugin
Warns when written code contains known-dangerous patterns
What it is
A plugin that appends security warnings to file-write results when new content includes risky patterns such as pickle.load, eval, os.system, verify=False or injection-prone workflow syntax.
Good for
- Catch unsafe code the agent writes
- Flag weak crypto modes
- Warn on dangerous deserialization
Worth knowingPattern-based warnings, so it can miss issues and flag harmless uses.
Sources
- https://github.com/NousResearch/hermes-agent/tree/HEAD/plugins/security-guidance (project README, read 13 Nov 2026)
- https://api.github.com/repos/NousResearch/hermes-agent (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.