perplexity
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from the web via Perplexity AI, creating a surface for indirect prompt injection.
- Ingestion points: Web search results and synthesized responses retrieved through
mcp__perplexity__perplexity_searchandmcp__perplexity__perplexity_ask. - Boundary markers: The instructions do not specify the use of delimiters or provide directives for the agent to ignore instructions contained within the retrieved web content.
- Capability inventory: The skill is part of an agentic workflow with capabilities to search the web and synthesize information, with related skills suggesting further processing (e.g.,
web-to-markdown,autoresearch). - Sanitization: No sanitization, validation, or content filtering mechanisms are defined for the data returned from external search queries.
Audit Metadata