bob-security-model

Use when the user asks why IBM Bob asks for approval, how approved or denied command patterns match (prefix, wildcard, case), what "Security warning" or…

Skill by elpfries

IndexedMIT

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/elpfries-bob-security-model

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Use when the user asks why IBM Bob asks for approval, how approved or denied command patterns match (prefix, wildcard, case), what "Security warning" or requiresSecurityApproval means, how to set up auto-approve or a yolo-like mode, or whether a given command would be auto-approved.

Use cases: security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/bob-security-model

What's inside

Skill name: bob-security-model
Description: Use when the user asks why IBM Bob asks for approval, how approved or denied command patterns match (prefix, wildcard, case), what "Security warning" or requiresSecurityApproval means, how to set up auto-approve or a yolo-like mode, or whether a given command would be auto-approved.
License: MIT
Instructions: 15 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Files (4)

SKILL.md
approvals.md · reference/
_bobcheck.py · scripts/
approval_check.py · scripts/

SKILL.md (first lines)

# Bob security model

1. "Would this be auto-approved?" / "why did it prompt?" →
   `python3 "<skill-dir>/scripts/approval_check.py" "<command>"` (`--settings PATH`,
   `--approved PAT`, `--denied PAT`). It runs the exact token matcher and the always-on regex
   heuristics; it cannot run the model check and it approximates the command split.
2. "How does it work?" → read `reference/approvals.md`: matching (token prefix, case-sensitive,
   no wildcards, longest pattern wins, tie → allow), the security check (heuristics → setting →
   model, fail-closed; approved lists never bypass it), yolo, enforcement.
3. Ground answers in the user's settings (`~/.bob/settings/settings.json`, workspace
   `.bob/settings.json`) and in `bob-telemetry security` for what was actually flagged.

Never suggest editing `extension.js`; never call `isCommandSecurityEnabled: false` harmless.

From elpfries/bob-sideshow, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Oct 19, 2026 (10 days ago)
Last release: Oct 19, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/elpfries/bob-sideshow
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from elpfries

Cite this page

bob-security-model skill. Agent Mart. https://agentmart.dev/skills/elpfries-bob-security-model (last updated 2026-10-24)