trend-scout

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code, unauthorized command execution, or data exfiltration patterns were detected. The skill's operations are confined to its defined memory management tasks.
  • [EXTERNAL_DOWNLOADS]: Fetches industry trends and source URLs from Perplexity, which is recognized as a well-known and legitimate service.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. 1. Ingestion points: Untrusted trend data is retrieved via the perplexity_ask tool. 2. Boundary markers: The skill does not use specific delimiters to wrap external content in the generated trend-angles.md file. 3. Capability inventory: The skill possesses file-write permissions for the creative-memory directory, and its outputs are consumed by other automated skills. 4. Sanitization: There is no evidence of data sanitization or instruction-filtering for the content retrieved from external search results.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:00 AM