The Agent Skills Directory

[SAFE]: The skill provides documentation and Python code snippets for interacting with the Vast.ai REST API. It utilizes the standard requests library and communicates with the legitimate service endpoint at https://cloud.vast.ai/api/v0. The implementation includes standard security practices such as using Bearer token authentication via headers.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting and processing external data from API responses.
Ingestion points: The RateLimitedVastClient class in SKILL.md parses external API responses using resp.json().
Boundary markers: None are present in the code snippets.
Capability inventory: The skill uses standard agent capabilities (Read, Write, Edit) but the provided Python logic is limited to status monitoring and data retrieval without calling dangerous functions like exec(), eval(), or subprocess.run() on the ingested data.
Sanitization: No specific sanitization or validation of the JSON schema is implemented in the example code, but the risk is minimized as the data is used for simple status comparisons.

vastai-rate-limits