Scanned repository says: The open-source Grok Bot alternative: your own team of AI bots, in a chat app.
Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.
Inspect GitHub sourceVotes show community interest, not safety. They never change this score.
Runtime safety, real-world agent capability, fitness for your use case or independent certification.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
The open-source Grok Bot alternative: your own team of AI bots, in a chat app.
README.md:5openmausbot.com · Download · Open source Grok Bot alternative, compared
README.md:7Every bot in the sidebar is a real agent — Claude or Codex running locally under the hood — with its own
README.md:11No explicit capability or integration was extracted; that does not mean none exists.
Manifest declares Node.js >=24 as a requirement.
package.json:20Declares a dependency on zod.
package.json:130Declares a dependency on @clack/prompts.
package.json:89Declares a dependency on @codemirror/lang-sql.
package.json:90Declares a dependency on @codemirror/language.
package.json:91Declares a dependency on @codemirror/state.
package.json:92Declares a dependency on @duckdb/node-api.
package.json:93Manifest declares Apache-2.0 as its license.
package.json:15These are references in selected source files, not proof that a feature works at runtime.
Read from commit 83c10b3 at Oct 12, 2026, 5:07 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.
Dependencies: 24 exact runtime versions from package.json checked against OSV.dev on Oct 12, 2026; 0 with known advisories. Reachability is not checked.
A SQL statement is assembled by inserting values into the query text. If any of those values comes from a user or from model output, as in text-to-SQL agents, it can rewrite the query.
Pass values as bound parameters and allow-list identifiers such as table and column names.
The code can delete data, send messages or move money, and no step asks a person to approve it first. A wrong model decision becomes a real action.
Require explicit human approval before a destructive or external action.
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.
Expose a clear Privacy Policy link on the official homepage.
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
Share the full report so its scope and limits travel with the score.
