alterlab-perplexity

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or unauthorized access patterns were found in any of the skill's scripts or documentation.
  • [DATA_EXPOSURE]: The skill manages the OpenRouter API key using secure practices such as environment variables and local .env files. The setup script correctly masks the key during validation.
  • [EXTERNAL_DOWNLOADS]: Dependencies are restricted to reputable and widely used libraries like litellm and python-dotenv.
  • [PROMPT_INJECTION]: Ingestion points: User search queries are processed by the search_with_perplexity function in scripts/perplexity_search.py. Boundary markers: No explicit delimiters are present to wrap the user input. Capability inventory: The skill performs network requests to the OpenRouter API and has local file-write access for creating environment configuration. Sanitization: No input sanitization is performed on the query string. This constitutes an inherent vulnerability surface common to search tools but is consistent with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:47 AM
Security Audit — agent-trust-hub — alterlab-perplexity