Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. `references/distribuciones-semanales.md` — los 4 modos de calendario y su distribución por día
Security audit
calendarizador-historias-formula100k
Security checks for vulnerabilities and agentic risk
Overview
This skill openly creates Instagram Stories calendars and local planning files, with no artifact evidence of hidden execution, exfiltration, destruction, or privilege abuse.
Install only if you expect a Spanish-language Instagram Stories planning workflow that saves calendars, script files, and spreadsheets locally. Review generated files before sharing them, especially if they include launch plans, offers, customer examples, or business strategy. The skill also relies on other Formula 100K skills for script generation, so those dependencies should be trusted separately.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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
Findings (10)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. `references/distribuciones-semanales.md` — los 4 modos de calendario y su distribución por día
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill mandates 'español neutro' and forbids other variants without checking the user's preference. This is not a classic security flaw, but it can override user intent and create unsafe automation behavior in multilingual or accessibility-sensitive contexts by forcing output transformations the user did not request.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The documentation says this skill 'NO genera guiones por sí misma,' but the same file defines a workflow where it calls
guionizacion-historias-formula100kfor every slot, waits for generated.mdscripts, stores their paths, and consolidates sections from those scripts. At the manifest level this means the skill effectively performs script generation as part of its delivered behavior, not merely calendar assembly.- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
Lines L003-L004 explicitly state that the skill does not generate scripts itself, yet later instructions require invoking the scripting skill for each slot, capturing the generated
.mdpath, and extracting production sections from those generated scripts. That is an intent-level contradiction in the documentation: the implementation workflow clearly includes generating scripts via orchestration.- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
Se ordena guardar paths y producir un .md maestro, lo que introduce persistencia de datos y referencias a archivos sin transparencia suficiente para el usuario. Si el contenido incluye información sensible de campañas, ofertas o estrategias, esa persistencia puede dejar rastros no deseados o facilitar exposición posterior.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The manifest describes a skill focused on assembling weekly Instagram story calendars and handing off sequencing to the scripting skill, but this file expands the behavior to producing
.xlsxor.csvdeliverables with multiple sheets and metrics. File generation is not just an implementation detail here; it is presented as a substantive output mode beyond the stated calendar-planning scope.- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
La skill instruye escribir archivos .xlsx/.csv en disco sin exigir aviso ni confirmación explícita del usuario sobre persistencia local. Esto puede provocar creación no consentida de archivos, exposición de datos comerciales o personales incluidos en el calendario, y comportamiento inesperado en entornos con acceso al sistema de archivos.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill explicitly instructs the agent to write calendar and script files to local paths, but the nearby warning only mentions image-generation cost and not file creation or persistence. This can surprise users by storing potentially sensitive business plans, launch details, or customer-related content on disk without explicit consent or a clear notice at the moment of action.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown file contains user-facing guidance exclusively in Spanish and does not indicate that the language is optional or limited to a Spanish-speaking audience. Under the natural-language policy check, forcing a specific language without user opt-in can be a locale-policy violation.
- Content
Static analysis
No suspicious patterns detected.