apify-yandex-image-search-api
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Yandex search results, such as image titles, hosting site snippets, and source text. This data is interpolated into the agent's context, which is a common surface for indirect prompt injection attacks.
- Ingestion points: External metadata is retrieved from the Apify platform using the
apify datasets get-itemscommand as described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or warning prompts to separate untrusted search data from the agent's core instructions.
- Capability inventory: The skill uses the
apifyCLI to execute hosted Actors and manage dataset retrieval. - Sanitization: There are no explicit instructions to sanitize or validate the text fields returned by the third-party scraper Actor before they are processed by the agent.
Audit Metadata