The Agent Skills Directory

[SAFE]: The skill functions as a dispatcher, delegating tasks to sub-skills. No malicious code, credential exposure, or unauthorized network activity was detected.
[PROMPT_INJECTION]: The skill uses the {{args}} variable to pass user input to sub-skills. While this is a standard pattern for routing skills, it constitutes an indirect prompt injection surface. * Ingestion points: {{args}} in SKILL.md. * Boundary markers: Not present. * Capability inventory: The skill configuration includes high-privilege tools like Bash and WebFetch. * Sanitization: Not present.

proof