Web Research
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection as it retrieves and analyzes content from arbitrary web URLs.\n
- Ingestion points: Data fetched via the
apify/rag-web-browsertool in Step 3 of theSKILL.mdworkflow.\n - Boundary markers: The skill lacks explicit instructions to treat retrieved text as untrusted data or delimiters to separate external content from agent instructions.\n
- Capability inventory: The skill allows the agent to read full page content and perform analysis, which could be manipulated by instructions embedded in the scraped pages.\n
- Sanitization: No input validation or sanitization of the fetched markdown content is specified.
Audit Metadata