Meta Ad Creatives

Security checks across static analysis, malware telemetry, and agentic risk

Overview

The skill is coherent with its stated Meta Ads analytics purpose, but users should notice that it requires Meta credentials and may persist ad performance data.

This skill appears purpose-aligned for Meta Ads performance reporting. Before installing, use a limited Meta access token, verify the source and Python dependencies, and decide whether historical client/account data should be stored in Firestore or only locally in SQLite.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

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.

#
ASI03: Identity and Privilege Abuse
Low
What this means

Installing or using the skill may give it access to Meta Ads account metrics allowed by the supplied token.

Why it was flagged

The skill uses Meta/Facebook credentials from the environment to access ad account data. This is expected for the stated analytics purpose, but it is sensitive account authority.

Skill content
access_token = os.getenv("FACEBOOK_ACCESS_TOKEN")
app_id = os.getenv("FACEBOOK_APP_ID")
app_secret = os.getenv("FACEBOOK_APP_SECRET")
Recommendation

Use a least-privilege Meta token limited to the ad accounts and read/reporting permissions needed, and keep the app secret out of shared logs or prompts.

#
ASI06: Memory and Context Poisoning
Low
What this means

Ad performance history may be saved locally or in Firestore and reused for later reporting.

Why it was flagged

The skill discloses persistent storage of historical ad performance data, including a cloud storage option. This fits trend analysis, but storage location and retention matter for business/client data.

Skill content
The skill stores historical data for trend analysis:
- **Firestore** (default for cloud deployments)
- **SQLite** (local fallback)
Recommendation

Confirm whether Firestore or SQLite will be used, who can access the stored data, and whether retention/deletion practices meet your organization’s requirements.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

Users have less context about the publisher/source and may need to manually ensure the Python environment contains safe dependencies.

Why it was flagged

The artifact has limited provenance and no install specification, while it includes executable Python code. No malicious behavior is evidenced, but provenance and dependencies should be verified before use.

Skill content
Source: unknown
Homepage: none
No install spec — this is an instruction-only skill.
Code file presence: scripts/meta_ad_creatives.py
Recommendation

Review the included code and install only trusted versions of required Python packages before running the examples.