apify-deploy-integration
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection because it is designed to ingest and process untrusted data from external web sources.
- Ingestion points: Untrusted content enters the agent context in
SKILL.mdwhen the skill fetches items from Apify datasets (e.g.,client.dataset(run.defaultDatasetId).listItems()). - Boundary markers: No delimiters or explicit instructions to treat the scraped content as untrusted data are provided in the code examples or instructions.
- Capability inventory: the skill environment is highly capable, with access to
Bash(includingapify,npm,vercel, andgcloudtools), and file system operations (Read,Write,Edit). - Sanitization: The provided integration examples do not include sanitization, validation, or filtering of the scraped data before it is consumed or potentially presented back to the agent.
Audit Metadata