perplexity
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable scripts or system-level commands, posing no risk of local privilege escalation or persistence.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from the web. This is inherent to the functionality of an AI search tool.
- [Ingestion points]: External web content fetched via the Perplexity API.
- [Boundary markers]: None specified in the prompt structure to distinguish between search results and instructions.
- [Capability inventory]: Web search, multi-step reasoning, and information synthesis.
- [Sanitization]: No explicit sanitization or filtering of remote content is implemented within the skill definition itself.
Audit Metadata