Zum Inhalt springen
TakoAPI
Zurück zu den Skills

permission-creep-scanner

von andyxinweiminicloud

PDF & Documents
311Downloadzahlen laut clawskills.sh
0Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

Helps detect permission creep in AI agent skills — flags when a skill's actual code accesses resources far.

Beschreibung

Was dieser Skill macht

Analyzes AI agent skill code to detect mismatches between a skill's declared purpose and what it actually accesses. Flags sensitive path reads, environment variable access, network calls, and subprocess spawning that fall outside stated functionality. Outputs a risk rating and itemized mismatch list.

Manual code review doesn't score the gap between what a skill claims to do and what it actually touches, so automated mismatch detection catches over-permissioned skills that look harmless from their descriptions alone.

Wann du ihn einsetzt

  • Auditing a third-party skill before adding it to an agent
  • Checking if a code formatter reads credential files
  • Scanning marketplace skills for undeclared network calls
  • Reviewing community-submitted skills before deployment
  • Catching hidden data exfiltration in utility tools

Beispiel-Workflow

EINGABE

User asks: scan this 'indent-fixer' skill that claims to fix Python indentation to 4 spaces

AGENT
  1. 1

    Parses skill name, summary, and description to extract declared scope

  2. 2

    Scans code for file reads, environment variable access, network calls, and subprocess usage

  3. 3

    Compares declared scope against observed access patterns

  4. 4

    Scores mismatch severity and identifies sensitive path violations

  5. 5

    Generates risk rating with per-finding explanations

AUSGABE

OVER-PERMISSIONED report listing 3 mismatches: ~/.env read, OPENAI_API_KEY extraction, and HTTP exfiltration with the key passed in the URL

Installation

clawhub install andyxinweiminicloud/permission-creep-scanner

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links