perplexity-cost-tuning

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill follows security best practices by using environment variables (e.g., $PERPLEXITY_API_KEY) for API authentication instead of hardcoding credentials.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the official Perplexity API (api.perplexity.ai). This is a well-known service and the interaction is necessary for the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external query data to perform model routing and caching logic. 1. Ingestion points: The 'query' parameter in the selectModel and cachedQuery functions in SKILL.md. 2. Boundary markers: None identified. 3. Capability inventory: Network access via curl to the Perplexity API. 4. Sanitization: None identified; query processing relies on regex matching and hashing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 09:38 PM
Security Audit — agent-trust-hub — perplexity-cost-tuning