Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 1 | ⚔ El Scroll-Stopper | `personas/scroll-stopper.md` | nadie se detiene en los primeros 3 segundos |
Security audit
consejo-contenido-formula100k
Security checks for vulnerabilities and agentic risk
Overview
This is a Spanish content-critique skill with optional reference research, and the inspected artifacts do not show hidden execution, persistence, destructive behavior, or data exfiltration.
Install this if you want a strongly opinionated Spanish-neutral content review workflow. Be aware that it may use web or Apify/Supadata lookups when you provide handles or keywords, and it may read local brand voice files if present, so avoid giving it private handles, unreleased campaign details, or sensitive brand material unless that is intended.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (19)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 1 | ⚔ El Scroll-Stopper | `personas/scroll-stopper.md` | nadie se detiene en los primeros 3 segundos |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 3 | 💰 El Vendedor | `personas/vendedor.md` | gusta pero no mueve a F100K (no vende) |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 3 | 💰 El Vendedor | `personas/vendedor.md` | gusta pero no mueve a F100K (no vende) |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 4 | 📊 El Algoritmo | `personas/algoritmo.md` | no genera señal de distribución (watch-time, saves, shares) |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 4 | 📊 El Algoritmo | `personas/algoritmo.md` | no genera señal de distribución (watch-time, saves, shares) |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 5 | 🎭 La Voz de la Marca | `personas/voz-marca.md` | suena a IA, a cualquiera, o rompe el ADN/español neutro |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 5 | 🎭 La Voz de la Marca | `personas/voz-marca.md` | suena a IA, a cualquiera, o rompe el ADN/español neutro |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 5 | 🎭 La Voz de la Marca | `personas/voz-marca.md` | suena a IA, a cualquiera, o rompe el ADN/español neutro |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Sigue el formato exacto de `templates/debate-format.md` (el debate) y `templates/verdict-format.md` (el veredicto). No improvises los banners.
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The instructions require all output to be in "español neutro" and prescribe specific regional variants ("tú, no vos; aquí, no acá") with no indication that the user can choose another language or locale. This is a natural-language policy issue because it imposes a fixed locale preference rather than offering or deferring to user preference.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The entire persona file is written in Spanish and provides no indication that language is optional, selectable, or limited to a justified Spanish-speaking context. Per the policy, a skill that effectively mandates a specific language without user opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The file defines the persona entirely in Spanish and instructs its voice and phrasing accordingly, which effectively imposes a language/locale on outputs. There is no indication that the user can opt into another language or that the Spanish-only constraint is required for a region-specific purpose.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This markdown file contains natural-language instructions and persona content exclusively in Spanish, but it does not indicate that the user opted into Spanish or that the skill is intended only for a Spanish-speaking context. Under the language/locale policy, forcing a specific language without user choice can be a policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The persona hard-codes 'español neutro' as a non-optional rule, which can override a user's preferred dialect or identity-marking language. In a content-generation skill, this creates an avoidable policy bias that can distort outputs, reduce user agency, and systematically exclude valid regional forms.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The blanket ban on regional Spanish forms ('cero argentinismos') enforces exclusionary normalization rather than context-sensitive editing. Because this skill is designed to critique and rewrite content, that rule can systematically erase user voice and produce biased outputs against certain Spanish-speaking communities.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The file's instructions are entirely in Spanish and direct the model to use an exact debate structure for every use, which effectively imposes a specific language/locale. There is no indication that users may opt into another language or that the Spanish-only constraint is required for a region-specific purpose.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
La instrucción "En español neutro siempre" fuerza una salida en un idioma/variante específica. Según la política, las restricciones de idioma deben ofrecer opt-in del usuario o estar claramente justificadas como limitación regional, y aquí no aparece ninguna de esas salvedades.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
La verificación exige que el gancho y CTA "estén en español neutro", consolidando una política de lenguaje obligatoria dentro del flujo del skill. No se ofrece alternativa basada en preferencia del usuario ni una justificación contextual visible para imponer esa variante.
- Content
Static analysis
No suspicious patterns detected.