Pizzaparty Automation

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Concern

ASI02: Tool Misuse and Exploitation

What this means

It could post automated, repetitive chat under the user's Twitch identity, affecting reputation or violating channel/platform rules.

Why it was flagged

The skill can send Twitch IRC chat messages to channels supplied at runtime, which is a public account action.

Skill content

def message(self, channel, msg):
        self._send(f"PRIVMSG #{channel.lower()} :{msg}")

Recommendation

Only run it for channels you explicitly choose, review the exact messages first, and add a confirmation or dry-run step before posting.

Concern

ASI03: Identity and Privilege Abuse

What this means

Anyone or any automation using those secrets may be able to send chat as the account or access linked service functionality.

Why it was flagged

The skill asks for account credentials and tokens that let it log in or act through the user's Twitch/Discord-linked identity.

Skill content

| PIZZAPARTY_PASSWORD | OAuth password |
| TWITCH_OAUTH_TOKEN | IRC token (oauth:xxx) |
| TWITCH_CLIENT_SECRET | App secret |

Recommendation

Avoid using personal-account secrets unless necessary, prefer a minimally scoped bot/test account if allowed, and require the skill metadata and runtime prompts to clearly declare all needed credentials.

Note

ASI10: Rogue Agents

What this means

If connected to an external scheduler, it may keep posting repeatedly without a fresh decision each time.

Why it was flagged

The skill includes a recurring four-times-daily schedule, although the provided code does not install or start a scheduler by itself.

Skill content

"sessions": [ { "time": "09:00", "duration": 15 }, ... { "time": "21:00", "duration": 15 } ]

Recommendation

Confirm how scheduled runs are started and disabled, and require renewed user approval for recurring posting.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Setup details and any future browser-scraping behavior are not fully visible in the provided artifacts.

Why it was flagged

The docs reference Playwright-based behavior and a configuration file, but the supplied manifest has no .env.example and no install spec for Playwright.

Skill content

Uses Playwright for dashboard scraping + Twitch IRC for chat.
...
- .env.example - Configuration

Recommendation

Ask the publisher to include all referenced configuration and dependency files, and to declare required credentials and dependencies before use.