check-virality

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill uses shell commands like grep, echo, and file existence checks ([ -f ], [ -d ]) to audit the codebase. These commands are non-destructive, do not use user-provided variables for command construction, and are restricted to read-only search operations.
  • DATA_EXFILTRATION (SAFE): No network operations (curl, wget, fetch) are present. The skill only identifies patterns related to social sharing and referrals without transmitting data externally.
  • PROMPT_INJECTION (SAFE): No instructions attempting to override agent behavior, bypass safety filters, or reveal system prompts were detected in the markdown or metadata.
  • DATA_EXPOSURE (SAFE): While the skill searches for 'referral' and 'invite' patterns, these are targeted at application logic rather than sensitive credentials or system-level secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM