agent-access-control

Stars9

Forks0

UpdatedJune 9, 2026 at 10:30

Apply user, stranger, group, channel, and action access tiers using native channel policy, allowlists, approvals, and cognitive review.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

bhaveshpabnani

bhaveshpabnani/Humungousaur

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Computer Occupations, All OtherComputer and Mathematical Occupations·SOC 15-1299

SKILL.md

readonly

name	agent-access-control
description	Apply user, stranger, group, channel, and action access tiers using native channel policy, allowlists, approvals, and cognitive review.

Agent Access Control

Purpose

Ensure the assistant responds and acts only for authorized people and contexts. Access control covers channel identity, groups, strangers, and high-risk actions.

When To Use

Use for channel onboarding, group chats, unknown senders, shared rooms, bot messages, external requests, and permission-sensitive tools.

Inputs And Evidence

Sender ID, channel ID, conversation type, allowlists, pairing state, and requested action.
Channel manifest and setup status.

Tool Map

channel_manifest
channel_setup_status
channel_doctor
ambient-room-context
bot-loop-protection
message-approval-policy

Workflow

Identify actor, channel, and conversation context.
Check allowlist/pairing/group policy.
Classify action risk and external visibility.
Let model-led cognition decide response posture within policy.
Suppress or draft rather than act when identity is uncertain.
Record setup gaps or policy needs.

Native Implementation Boundaries

Use Humungousaur channel policy and approval tools.
Do not import external reference agent-access-control code.
Do not make semantic access decisions with keyword matching.

Safety And Approval

Unknown users get limited or no action.
High-risk tools need approval even for trusted users.
Group contexts require stricter visible-reply policy.

Verification

Channel manifest/status proves policy support.
Prepared/suppressed outcomes should have reasons.
Send claims require native send status.

Failure Modes

Treating display names as identity proof.
Giving group members DM-level access.
Ignoring bot-loop signals.

References

Shortlist item: agent-access-control.

More from this repository

same repository

platform-collector-development

bhaveshpabnani/Humungousaur

Design, implement, organize, document, and verify Humungousaur platform OS collectors for macOS, Windows, or Linux using official OS API references, shared event envelopes, helper health, privacy-first metadata, and repo-native adapter boundaries.

2026-06-119

software-engineering

bhaveshpabnani/Humungousaur

Parent skill for code inspection, debugging, tests, CI, reviews, dependency security, skill authoring, experiments, and engineering workflows.

2026-06-119

agent-self-assessment

bhaveshpabnani/Humungousaur

Assess the assistant's readiness, capability fit, safety risks, tool coverage, and verification plan before or during complex work. Use when work is high-impact, ambiguous, risky, long-running, or failure-prone.

2026-06-099

agent-self-reflection

bhaveshpabnani/Humungousaur

Review recent agent behavior, uncertainty, mistakes, interaction quality, and lessons so the assistant can improve future work. Use after complex tasks, failures, user corrections, or long sessions.

2026-06-099

ambient-room-context

bhaveshpabnani/Humungousaur

Treat unmentioned group-room chatter as quiet context unless policy, mention, direct request, or model-led cognition decides a response is appropriate. Use for Slack channels, Discord servers, Telegram groups, Matrix rooms, and similar shared spaces.

2026-06-099

approval-gated-external-actions

bhaveshpabnani/Humungousaur

Require explicit human approval before purchases, messages, installs, file writes, remote API mutations, app control, or other irreversible actions.

2026-06-099

name	agent-access-control
description	Apply user, stranger, group, channel, and action access tiers using native channel policy, allowlists, approvals, and cognitive review.

Agent Access Control

Purpose

Ensure the assistant responds and acts only for authorized people and contexts. Access control covers channel identity, groups, strangers, and high-risk actions.

When To Use

Use for channel onboarding, group chats, unknown senders, shared rooms, bot messages, external requests, and permission-sensitive tools.

Inputs And Evidence

Sender ID, channel ID, conversation type, allowlists, pairing state, and requested action.
Channel manifest and setup status.

Tool Map

channel_manifest
channel_setup_status
channel_doctor
ambient-room-context
bot-loop-protection
message-approval-policy

Workflow

Identify actor, channel, and conversation context.
Check allowlist/pairing/group policy.
Classify action risk and external visibility.
Let model-led cognition decide response posture within policy.
Suppress or draft rather than act when identity is uncertain.
Record setup gaps or policy needs.

Native Implementation Boundaries

Use Humungousaur channel policy and approval tools.
Do not import external reference agent-access-control code.
Do not make semantic access decisions with keyword matching.

Safety And Approval

Unknown users get limited or no action.
High-risk tools need approval even for trusted users.
Group contexts require stricter visible-reply policy.

Verification

Channel manifest/status proves policy support.
Prepared/suppressed outcomes should have reasons.
Send claims require native send status.

Failure Modes

Treating display names as identity proof.
Giving group members DM-level access.
Ignoring bot-loop signals.

References

Shortlist item: agent-access-control.