Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > - Guarda en `guiones/historias/` respetando al pie de la letra `references/output-template.md`: otra skill lo parsea.
Security audit
guionizacion-historias-formula100k
Security checks for vulnerabilities and agentic risk
Overview
This is a Spanish Instagram story-script writing skill with disclosed file output and Telegram delivery, and I found no hidden code, destructive behavior, credential handling, or deceptive instructions.
Install if you want an OpenClaw skill that generates Spanish-neutral Instagram story scripts and stores them as markdown. Before using it with sensitive business material, remember that it may read profile or Segundo Cerebro context, save a draft file under guiones/historias, and deliver the full document through Telegram.
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
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (12)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > - Guarda en `guiones/historias/` respetando al pie de la letra `references/output-template.md`: otra skill lo parsea.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > - Guarda en `guiones/historias/` respetando al pie de la letra `references/output-template.md`: otra skill lo parsea.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 4. `references/ctas.md` — guía de CTAs con consecuencia
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 4. `references/ctas.md` — guía de CTAs con consecuencia
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
El disparador 'o cualquier variación' hace que la activación de la skill sea demasiado amplia y ambigua, lo que puede provocar invocaciones no deseadas ante solicitudes parcialmente relacionadas. En un agente con acceso a lectura/escritura y envío por Telegram, esa sobre-activación puede terminar generando, guardando o compartiendo contenido sin que el usuario haya querido usar esta skill en primer lugar.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
La skill indica que guardará la salida en
guiones/historias/pero no presenta una advertencia visible ni una confirmación explícita previa sobre escritura en disco. Esto reduce la transparencia y puede causar persistencia involuntaria de contenido sensible, borradores comerciales o datos del negocio del usuario.- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
La instrucción de entregar el resumen y el
.mdpor Telegram implica transmisión de contenido a un servicio externo, pero no informa claramente al usuario ni pide consentimiento. Si el guion incorpora información del 'Segundo Cerebro', perfil o datos del negocio, existe riesgo de exfiltración accidental de contenido sensible o propietario.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
El archivo establece una política lingüística obligatoria: todo el output debe usar español neutro y reemplazar formas argentinas, incluso si aparecen naturalmente en la variante del usuario. Esto fuerza una preferencia de idioma/locale sin ofrecer opción o consentimiento, lo que encaja con una violación de política de lenguaje/locale.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown file presents all instructions, examples, and checklist items exclusively in Spanish, and does not indicate that the skill is intended only for Spanish-speaking users or provide any user opt-in for language selection. That can violate a language/locale policy when users are not given a choice or the restriction is not justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown content appears to force a specific language for the skill material, which can violate language/locale policy when no user opt-in or alternative is provided. There is no indication that the skill is region-specific or that Spanish is an intentional, documented constraint.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The title and instructions require the output file to follow an exact format written in Spanish, and line L003 states the skill must always save output in this exact format. This creates a language/locale constraint without any opt-in or documented region-specific justification, which matches the policy-violation criteria.
- Content
Static analysis
No suspicious patterns detected.