AGENT SKILL

permission-boundary-review

Reviews authorization, tenant isolation and privileged route boundaries. Use when docs or route inventories describe privileged actions, admin surfaces, policy checks or tenant-specific data.

License 许可
MIT
所属仓库
Eliyce/paqad-ai
最近更新
2026-11-13
Stars
★ 8
Forks
0

01 前言 Front Matter

name
permission-boundary-review
metadata
{ "cacheable": "false", "model_tier": "reasoning", "paqad-meta": "skill.meta.yaml", "output_format": "markdown" }
description
Reviews authorization, tenant isolation and privileged route boundaries. Use when docs or route inventories describe privileged actions, admin surfaces, policy checks or tenant-specific data.

02 资源文件 7

03 SKILL.md 正文

What It Does

Reviews permission, authorization, and tenant-boundary expectations so pentest findings can focus on real access-control gaps instead of generic auth reminders.

Use This When

When module docs or route inventories describe privileged actions, admin surfaces, policy checks, or tenant-specific data handling.

Inputs

  • Read the module docs that describe privileged flows first.
  • Read references/boundary-checklist.md before deciding whether evidence is sufficient.
  • Read tests and route evidence that show how the project enforces those boundaries.

Procedure

  1. Run scripts/scan-authz-smells.sh to surface candidate IDOR / hidden-admin / impersonation / broad-export / cross-tenant patterns.
  2. For each hit, walk the relevant module docs to determine whether code, tests, or runtime evidence proves the boundary.
  3. Bucket each finding into an area from assets/area-rubric.txt (idor, privilege-escalation, tenant-isolation, hidden-admin, impersonation, broad-export).
  4. Treat doc-vs-implementation disagreement as a security finding, never a benign inconsistency.
  5. Format per assets/output.template.md; validate with scripts/lint-findings.sh.

Output Contract

  • Match assets/output.template.md: severity, WSTG-AUTHZ id, area from assets/area-rubric.txt, Evidence, Missing proof, Required action.
  • Output must pass scripts/lint-findings.sh (exit 0).

Escalate / Stop Conditions

  • Ask when the privilege model is unclear or not described anywhere in the project.
  • Warn when runtime evidence suggests a privileged path is exposed without clear protection.
  • Do not mark a boundary as safe purely because authentication exists.

Resources

  • references/boundary-checklist.md
  • scripts/scan-authz-smells.sh
  • scripts/lint-findings.sh
  • assets/output.template.md
  • assets/area-rubric.txt
  • agents/openai.yaml

04 同仓库更多 Skills

Eliyce
Eliyce/paqad-ai

sample-skill

Sample bundled skill fixture

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

understand-idea

Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.

★ 8
Eliyce
Eliyce/paqad-ai

size-work

Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks "how big is this?", "roughly how much work is ABC-12?", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says "set it", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.

★ 8
Eliyce
Eliyce/paqad-ai

refine-ticket

Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up ("this ticket is vague", "fix up ABC-12", "split this, it's too big"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit "apply it" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.

★ 8