meta-ads

ISSUES FOUND max severity CRITICALSkillSpector Do not install 100 registry hoodini last scanned 2026-05-09 1 scan

13 findings (5 critical, 7 medium, 1 info), mainly data exfiltration, unauthorized tool use, policy violation. Most recent scan 2026-05-09.

Findings13

Critical5

High0

Medium7

Low0

Analyzersstatic bytecode pipeline behavioral trigger

Second scanner: NVIDIA SkillSpector

VerdictDo not install 100

Score100 / 100

Issues36

CategoriesPrivilege Escalation Data Flow Supply Chain

Version2.12.0 (static)

Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Pull, analyze, manage, and CREATE Meta ads (Facebook, Instagram, Messenger, Threads, Click-to-WhatsApp) via the Marketing API. Use when the user mentions Meta/FB/IG ads, Ads Manager, ROAS, CPA, CPM, CTR, ad spend, campaign or ad set performance, creative fatigue, frequency, CTWA, audience/placement breakdowns, A/B ad tests, or wants to pause an ad, change a budget, duplicate a winner, or launch a new campaign from scratch. Trigger on Hebrew terms like פרסום בפייסבוק/באינסטגרם, פרסומות מטא, ביצועי קמפיין, פרסומות, צור קמפיין, השק קמפיין, A/B טסט. Trigger on questions like how are my ads…

Package: 22 files, 174 KB
SKILL.md: 2406 words, 12+ sections
Code: Python (13)

SKILL.md covers: Meta Ads (Marketing API) · When to consult this skill · Three things to internalize before touching any script · The 37-month data wall · Before anything else: check setup + discover accounts · How to guide a user through setup (first-timers) · Path A vs Path B: which token type? · Workflow: read operations · Workflow: write operations (pause, budget, duplicate) · Workflow: creating a campaign from scratch · When NOT to use `create_campaign.py` · Gotchas the scripts already handle for you

Findings

CRITICAL Cross-file env var exfiltration: 3 files Data Exfiltrationbehavioral

Environment variable access with network calls in scripts/exchange_token.py, scripts/meta_client.py

Remediation: Review data flow across files: scripts/create_campaign.py, scripts/meta_client.py, scripts/exchange_token.py

CRITICAL Cross-file exfiltration chain: 3 files Data Exfiltrationbehavioral

Multi-file exfiltration chain detected: scripts/exchange_token.py, scripts/meta_client.py collect data → encode → scripts/exchange_token.py, scripts/meta_client.py, scripts/create_campaign.py transmit to network

Remediation: Review data flow across files: scripts/create_campaign.py, scripts/meta_client.py, scripts/exchange_token.py

CRITICAL Environment variable access with network calls detected Data Exfiltrationbehavioral

Script accesses environment variables and makes network calls in ../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/exchange_token.py

../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/exchange_token.py

Remediation: Remove environment variable harvesting or network transmission

CRITICAL Environment variable access with network calls detected Data Exfiltrationbehavioral

Script accesses environment variables and makes network calls in ../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/meta_client.py

../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/meta_client.py

Remediation: Remove environment variable harvesting or network transmission

CRITICAL PROMPT INJECTION detected by YARA Prompt Injectionstatic

Detects coercive prompt injections in tool description fields: hidden input

scripts/exchange_token.py:76

help="Short-lived user token. If omitted, you'll be prompted (hidden input).",

Remediation: Review and remove prompt injection pattern

MEDIUM Undeclared network usage Unauthorized Tool Usestatic

Skill code uses network libraries but doesn't declare network requirement

../skills/hoodini-ai-agents-skills/skills/meta-ads/SKILL.md

Remediation: Declare network usage in compatibility field or remove network calls

MEDIUM Environment variable harvesting detected Data Exfiltrationbehavioral

Script iterates through environment variables in ../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/exchange_token.py

../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/exchange_token.py

Remediation: Remove environment variable collection unless explicitly required and documented

MEDIUM Environment variable harvesting detected Data Exfiltrationbehavioral

Script iterates through environment variables in ../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/meta_client.py

../skills/hoodini-ai-agents-skills/skills/meta-ads/scripts/meta_client.py

Remediation: Remove environment variable collection unless explicitly required and documented

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.post(

scripts/create_campaign.py:108

resp = requests.post(url, data=data, files=files, timeout=120)

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.get(

scripts/exchange_token.py:47

resp = requests.get(url, params=params, timeout=30)

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.request(

scripts/meta_client.py:129

resp = requests.request(method, url, params=params, data=data, timeout=60)

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.get(

scripts/meta_client.py:189

resp = requests.get(next_url, timeout=60)

Remediation: Ensure network operations are necessary and document allowed destinations

INFO Skill does not specify a license Policy Violationstatic

Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.

SKILL.md

Remediation: Add 'license' field to SKILL.md frontmatter (e.g., MIT, Apache-2.0)

What is in the package

22 files, 174 KB. Show the list.

File	Kind	Size
`SKILL.md`	doc	17 KB
`requirements.txt`	doc	15 B
`assets/env.template`	other	1.5 KB
`references/analysis-playbooks.md`	doc	9.7 KB
`references/campaign-creation.md`	doc	10 KB
`references/insights-fields.md`	doc	7.7 KB
`references/setup.md`	doc	16 KB
`references/troubleshooting.md`	doc	14 KB
`references/write-actions.md`	doc	12 KB
`scripts/anomaly_detect.py`	script	6.9 KB
`scripts/auth_check.py`	script	4.3 KB
`scripts/create_campaign.py`	script	19 KB
`scripts/creative_fatigue.py`	script	7.4 KB
`scripts/duplicate_ad.py`	script	4.6 KB
`scripts/exchange_token.py`	script	5.2 KB
`scripts/fetch_insights.py`	script	8.9 KB
`scripts/list_accounts.py`	script	7.0 KB
`scripts/list_campaigns.py`	script	2.7 KB
`scripts/meta_client.py`	script	8.7 KB
`scripts/pause_ad.py`	script	3.2 KB
`scripts/rollback_creation.py`	script	2.8 KB
`scripts/update_budget.py`	script	5.8 KB

External hosts referenced

developers.facebook.com www.python.org business.facebook.com graph.facebook.com

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

META_AD_ACCOUNT_ID META_ACCESS_TOKEN META_APP_ID META_APP_SECRET META_API_VERSION

Package contents recorded 2026-10-22 at commit f7a43d8f8525. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Bytecode analyzer.
Pipeline analyzer.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://github.com/hoodini/ai-agents-skills
Raw scan result: skills-meta-ads-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/hoodini-meta-ads.svg)
Request a re-scan

Second scanner: NVIDIA SkillSpector

What this skill does

Findings

What is in the package

External hosts referenced

Environment variables referenced

What we checked

What we did not check

Sources

Related skills