perplexity

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill defines patterns for ingesting untrusted data from the web via Perplexity search tools, creating a vulnerability surface where external content could influence agent behavior.
  • Ingestion points: External data enters the context through mcp__perplexity__perplexity_search and mcp__perplexity__perplexity_ask outputs.
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings for the agent to ignore instructions embedded in the search results.
  • Capability inventory: The skill allows for searching, synthesizing web information, and referencing other MCP tools (Context7, Graphite, Nx).
  • Sanitization: No sanitization or validation of the retrieved web content is implemented within these instructions.
  • No Code (SAFE): The skill consists entirely of markdown documentation and tool usage guidelines. It does not include any scripts, executable binaries, or package manager files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 11:27 PM