social-writer

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on natural language generation and does not contain any executable code, shell commands, or external dependencies.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from MEMORY.md and USER.md. While these ingestion points lack explicit boundary markers or sanitization, the skill possesses no capabilities (such as file writing, network access, or command execution) to exploit, rendering the surface harmless.- [SAFE]: No instances of prompt injection, obfuscation, or credential harvesting were detected in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:55 AM
Security Audit — agent-trust-hub — social-writer