apify-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates web scraping which involves ingesting data from arbitrary web pages.\n
- Ingestion points: The requestHandler in SKILL.md and references/implementation.md extracts content like titles and prices from external URLs.\n
- Boundary markers: There are no markers or instructions provided to delimit scraped content or prevent the agent from following instructions found within the scraped data.\n
- Capability inventory: The skill environment has access to Read, Write, and Edit tools, and the code uses Actor.pushData to write to Apify datasets.\n
- Sanitization: No input validation or output sanitization of the scraped content is implemented in the provided optimization logic.
Audit Metadata