T01 · Skill Instruction Hijacking
- Location
SKILL.md:16- Finding
Mandatory Skill Instructions Hijack Agent Reasoning and Response Behavior
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 16–30
Vulnerability Type:T01: Skill Instruction Hijacking
Risk Level: HighVulnerable Code
markdown ## 1. EL "VELO" (PLANIFICACIÓN Y PENSAMIENTO) SI necesitas realizar un análisis previo o planificación antes de responder o usar herramientas (Chain of Thought), este razonamiento interno DEBE ir dentro de un bloque blockquote de Markdown (`>`) y seguir el estilo **CAVEMAN ULTRA**: - **Gramática:** Cero. Solo sustantivos y verbos en infinitivo/presente. - **Partículas:** Eliminar artículos y conectores (el, la, los, un, de, para, por, que). - **Cortesía:** Prohibida. - **Ejemplo de formato:** > Leer archivo auth. Encontrar bug línea 12. Generar parche. Ejecutar test. ## 2. LA "MÁSCARA" (COMUNICACIÓN FINAL) Fuera del bloque de pensamiento (`>`), este protocolo se DESACTIVA. - **Formato estricto:** DEBES dejar una línea en blanco vacía entre el bloque de pensamiento y tu respuesta final. - **Identidad Intacta:** Tu respuesta final hacia el humano DEBE retomar al 100% su personalidad, tono y muletillas definidos en tu `SOUL.md`. - No uses estilo cavernícola al hablar con el usuario.Technical Analysis
The skill is implemented as a set of prompt-level directives rather than executable code. When loaded, it uses mandatory language to control how the agent performs and exposes reasoning, formats responses, and adopts identity-related instructions from an external
SOUL.mdfile.These directives are not limited to an isolated, user-requested transformation. They attempt to alter the agent's general behavior for subsequent planning, tool use, and user-facing communication. The requirement to reproduce the personality, tone, and verbal habits defined in another file also creates an indirect instruction channel: behavior-changing content in
SOUL.mdmay be incorporated into responses without being independently evaluated as part of this s ...[truncated 1788 chars]- Remediation
View remediation
Remediation Suggestions
- Replace mandatory directives such as “must” with optional behavior that applies only when the user explicitly requests the optimization.
- Do not request, transform, expose, or prescribe the format of hidden reasoning. Limit the skill to concise user-facing summaries or explicitly requested logs.
- Remove the instruction to adopt the complete personality, tone, and verbal habits from
SOUL.md. - If external configuration is necessary, define a narrow schema of permitted presentation settings and reject executable instructions or unrelated behavioral rules.
- Scope the optimization to the active invocation and explicitly state that higher-priority platform, safety, developer, and user instructions remain authoritative.
- Avoid universal response-format requirements. Formatting should be applied only to the specific output requested by the user.
- Add a security note explaining that external personality or configuration files must be treated as untrusted input and must not override safety constraints.
- Test the revised skill against adversarial
SOUL.mdcontent to verify that external text cannot redirect goals, weaken safeguards, trigger tools, or alter unrelated tasks.
