The Agent Skills Directory

[SAFE] (SAFE): The skill uses environment variables (PH_API_TOKEN) for authentication rather than hardcoding credentials.
[COMMAND_EXECUTION] (SAFE): Uses curl to interact with the Product Hunt GraphQL API. This is the primary intended purpose of the skill and is implemented using standard parameters.
[Indirect Prompt Injection] (LOW): The skill processes user-generated content from Product Hunt, such as product descriptions and comments, which constitutes a potential attack surface.
Ingestion points: API responses processed in SKILL.md.
Boundary markers: Absent; data is interpolated into the agent's output context without specific delimiters.
Capability inventory: Limited to exec with curl for API requests; no file-system write or arbitrary code execution capabilities identified.
Sanitization: None specified; the agent treats API output as data to be formatted.

producthunt