Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. Use este `SKILL.md` como roteador.
Security audit
Meta Ads Super Manager Skill
Security checks for vulnerabilities and agentic risk
Overview
This skill is coherent for Meta Ads management, but it can change live ad accounts and upload customer audience data without a clear privacy gate.
Review before installing. Use this only with a Meta Ads MCP setup where you are comfortable granting campaign and audience write authority. Require explicit approval and a change preview before create/update/delete actions, and do not upload CRM or customer lists unless consent, lawful basis, hashing/minimization, and platform-policy requirements have been verified.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (24)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill documentation is written entirely in Portuguese, including usage guidance and operational principles, with no indication that the user can choose another language or that the skill is intentionally restricted to a Portuguese-speaking context. This creates a natural-language policy concern because it implicitly enforces a locale without opt-in or justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The manifest metadata sets
language":"pt-BR", and the rest of the skill content is written in Portuguese without any indication that users may choose another language. This creates a natural-language policy concern because it imposes a locale/language by default rather than documenting it as optional or region-specific.- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The instruction 'Execute imediatamente apos qualquer escrita.' defines a trigger as any write operation, which is very broad and does not clarify what kinds of writes are in scope. The file provides no negative examples or constraints to distinguish intended invocations from incidental or low-risk writes.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The checklist content is written entirely in Portuguese, including imperative instructions and user-communication requirements, with no indication that the skill supports other languages or that Portuguese is required for a specific region or compliance context. This can violate language/locale policy because it imposes a specific language without user opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The user-facing instructional text is written entirely in Portuguese, including checklist items and section headings, with no indication that language selection is optional or that the file is intended only for a Portuguese-speaking context. This creates a natural-language policy issue under the language/locale rule because it imposes a specific language without opt-in.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown file describes prompts to trigger workflows but only says they are 'short prompts to trigger skill workflows' and then lists example utterances. It does not define whether these are the only supported triggers, provide negative examples, or explain boundaries that prevent unintended activation from similar everyday requests.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The prompt explicitly encourages uploading CRM user data and generating lookalike audiences without any warning about personal data handling, lawful basis, consent, hashing requirements, or platform policy constraints. In an ads-management skill, this is materially risky because it can normalize transferring customer data into advertising systems without privacy review, leading to privacy violations, policy breaches, or accidental exposure of sensitive customer records.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file's instructional content is written entirely in Portuguese, which imposes a specific language on users. The file does not mention that Portuguese is optional, provide alternatives, or justify a region-specific constraint, so it appears to violate the language/locale policy.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file's instructional content is entirely written in Portuguese, which imposes a specific language on users without offering an opt-in, alternative locale, or stating that the skill is intended only for a Portuguese-speaking audience. This matches the policy category for language or locale constraints expressed in natural language.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The safety policy is entirely in Portuguese while the skill metadata and evaluation context are not guaranteed to be Portuguese, and the file does not declare a locale requirement or provide an alternate language. For a safety-critical write policy, this can cause operators or downstream agents to misunderstand confirmation, rollback, and risk-control requirements, leading to unsafe campaign changes or destructive actions without proper safeguards.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown file presents the skill instructions entirely in Portuguese, which effectively forces a specific language on users. The policy allows locale constraints only when they are optional or clearly justified, and neither condition is stated here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file’s instructional content is presented entirely in Portuguese, which effectively forces a specific language for users. The policy allows locale constraints only when they are justified or when users are given a choice, neither of which is present here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file's instructional content is written in Portuguese, which imposes a specific language choice on users or maintainers without offering an alternative or stating that the skill is intentionally region-specific. This matches the policy category for language or locale constraints lacking opt-in or justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The entire workflow is written in Portuguese and provides no indication that language choice is optional or based on user preference. Under the policy, a skill should not impose a specific language or locale without opt-in or clear justification.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The invocation guidance 'Use quando o usuario quer sair de ideia para estrutura executavel' is broad enough that the skill may be triggered for many loosely related requests without clear guardrails or preconditions. In a skill that can create campaigns, ad sets, creatives, and upload assets, over-broad activation increases the chance of unintended write actions, premature campaign setup, or actions taken without sufficient user confirmation and account-scoping.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
Natural-language instructions throughout the file are presented only in Portuguese, which can force a specific language on users without opt-in. The file does not indicate that the skill is intended solely for a Portuguese-speaking or region-specific context.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The workflow explicitly instructs operators to call update_campaign, update_adset, and update_ad on live advertising entities, but it does not require an explicit confirmation step, dry-run, change preview, or user warning about production impact. In a skill designed to orchestrate Meta Ads operations, this creates a real risk of unintended spend changes, audience disruption, delivery loss, or performance regression from autonomous or overly eager execution.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The workflow explicitly instructs the agent to perform live write operations against campaigns, ad sets, ads, and creatives in a daily operations routine, but it does not warn that these are production changes or require explicit user confirmation before execution. In an ads-management skill, these actions can immediately alter spend, delivery, targeting, or creative assets, so omission of change-safety guardrails materially increases the risk of unintended business impact.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This markdown file contains natural-language content in Portuguese, which can constitute a language/locale policy issue when the skill documentation forces a specific language without user opt-in. There is no visible indication in this file that the locale is optional or justified as region-specific.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file content is written entirely in Portuguese and does not indicate that language selection is optional or limited to a justified region-specific use case. This can violate language/locale policy when a skill implicitly requires a specific language without user opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
All headings and prompt examples are written in Portuguese, and the file gives no indication that other languages are supported or that Portuguese is required for a region-specific reason. This can violate language/locale policy when a skill effectively constrains interaction language without user opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This markdown file contains user-facing natural-language templates entirely in Portuguese, including headings and response structure, but does not indicate that the skill is region-specific or that users may opt into another language. That can violate a language/locale policy where skills must not force a specific language without user choice or justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
Natural-language instructions such as 'Use para rotina diaria de monitoramento, escala e manutencao' and the remaining operational steps are presented only in Portuguese. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a language/locale policy violation.
- Content
Static analysis
No suspicious patterns detected.