Is genpark-campaign-autopilot safe to install?

SaferSkills independently audited genpark-campaign-autopilot (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

SKILL.md · 1 file

SKILL.md1.5 KB · Markdown

name: genpark-campaign-autopilot

description: An autonomous agent skill that continuously monitors campaign performance, scales winning ad campaigns, and reverts based on custom guardrails.

GenPark Campaign Autopilot Skill

Overview

This skill allows GenPark agents to act as an autonomous campaign manager, mirroring the capabilities of GrowthGPT's "Autopilot". It continuously evaluates active campaigns across platforms (Meta, Google, TikTok), applying deterministic guardrails and logic to either scale budgets for winning campaigns or pause/revert campaigns that exceed target CPA.

Capabilities

Real-Time Monitoring: Fetches campaign data on a recurring cadence (e.g., last 72h window) to evaluate signals against targets.
Autonomous Scaling: Adjusts daily budgets dynamically (e.g., +20%) when ROAS and CPA signals are green and frequency is safe.
Safety Guardrails & Revert Triggers: Monitors performance post-scale. If CPA/CPP exceeds targets or CTR drops > 15%, the agent autonomously reverts the budget to the previous safe baseline.
Explainable Actions: Generates an auditable "Reasoning" report for every action (Context -> Reasoning -> Action -> Next Check).

Usage Instructions

Provide the agent with connection credentials to the relevant ad platform APIs (Meta Ads, Google Ads).
Define the exact targets (target_cpa, target_roas) and safety limits (max_daily_budget, revert_trigger_cpa).
Set the evaluation frequency (e.g., every 6 hours).

genpark-campaign-autopilot— agent skill

Is genpark-campaign-autopilot safe to install?

GenPark Campaign Autopilot Skill

Overview

Capabilities

Usage Instructions

Audit the pieces. Scan the whole. Decide.