zaker-news-search
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with the official ZAKER API at
https://skills.myzaker.com/api/v1/article/searchto retrieve news content. This activity is restricted to the vendor's own infrastructure and is essential for the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays titles and summaries from external news articles retrieved via the API. While this constitutes an attack surface for indirect prompt injection if an article contains malicious instructions, the skill does not possess sensitive capabilities (such as file writing, credential access, or arbitrary command execution) that could be leveraged for an exploit.
- Ingestion points: Data enters the context from the
data.listfield of the API response inscripts/search.pyandSKILL.md. - Boundary markers: The instructions in
SKILL.mdspecify a structured output format (e.g.,| {title} {summary}) which helps the agent distinguish between news content and instructions. - Capability inventory: The skill only performs simple GET requests and prints text; it does not utilize tools for local system modification or persistence.
- Sanitization: The skill does not perform explicit sanitization of the retrieved text, but the limited scope of the agent's tools in this context mitigates the risk.
Audit Metadata