monitoring-tech-acquisition-news-google
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted search result data from Google, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Search results retrieved from the
apidojo/google-search-scraperactor in Step 2. - Boundary markers: Absent; there are no specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded within search results.
- Capability inventory: The skill classifies, scores, and formats the external data into tables.
- Sanitization: No sanitization or filtering of the search result content is specified.
- [DYNAMIC_EXECUTION]: The
customMapFunctioninput parameter allows for the execution of arbitrary JavaScript code strings within the Apify actor environment. While this is an intended feature of the underlying scraper tool for data transformation, it involves dynamic execution of code provided via the skill's input.
Audit Metadata