data-scraper-agent
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest data from arbitrary public sources (websites, APIs) and pass this content directly to an LLM for scoring and summarization. This creates an attack surface for indirect prompt injection.\n
- Ingestion points: The
scraper/sources/scripts are intended to fetch data from any user-defined external URL.\n - Boundary markers: The prompt construction logic in
ai/pipeline.pylacks explicit delimiters or instructions to the model to ignore potential commands embedded within the scraped data.\n - Capability inventory: The agent has the ability to write data to external services (Notion, Supabase) and perform git operations (commit and push) within the GitHub Actions environment.\n
- Sanitization: The implementation does not include sanitization or validation of the scraped text to filter out malicious instructions before processing.
Audit Metadata