soros-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, data exfiltration, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of providing an analytical perspective.
  • [NO_CODE]: The skill consists entirely of markdown instructions and documentation. It does not include any scripts (.sh, .py, .js) or executable components that could perform actions on the host system.
  • [PROMPT_INJECTION]: While the skill defines a specific persona ('Soros perspective'), it does so through standard instructional framing. There are no attempts to override agent safety filters, extract system prompts, or bypass platform constraints.
  • [EXTERNAL_DOWNLOADS]: The README mentions an installation command (npx skills add) which is standard for the platform and refers to the author's own repository. No suspicious remote script execution (e.g., curl to bash) is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 02:51 AM
Security Audit — agent-trust-hub — soros-perspective