The Agent Skills Directory

[SAFE]: Analysis of the skill's core logic and instructions confirms it is designed for marketing and developer relations guidance. It contains no commands for privilege escalation, data exfiltration, or persistence.
[EXTERNAL_DOWNLOADS]: The skill references the official Product Hunt help center at help.producthunt.com/llms.txt to fetch updated platform guidelines. This is a legitimate reference to a well-known service's public documentation.
[INDIRECT_PROMPT_INJECTION]: The skill defines an interview workflow that ingests product and company details from the user. While this creates a data ingestion surface, the risk is minimal given the skill's limited capabilities.
Ingestion points: Product details and company history collected via the 'Interview' section in SKILL.md.
Boundary markers: The skill specifies asking one question per message, which helps maintain clear conversational boundaries.
Capability inventory: The skill does not possess capabilities for subprocess execution, file-system modification, or arbitrary network requests (beyond document retrieval).
Sanitization: No explicit sanitization or filtering of input is mentioned; however, the skill's output is restricted to text-based planning and predefined templates.

producthunt-playbook