skills/inklate/social-skills/hooks/Gen Agent Trust Hub

hooks

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the instructions and metadata revealed no evidence of prompt injection, obfuscation, or malicious intent.- [SAFE]: The skill does not utilize network protocols, shell commands, or external script execution.- [SAFE]: Potential Indirect Prompt Injection surface: The skill processes user-supplied post drafts and local configuration files (social-context.md). However, as the skill possesses no capabilities for external communication or system interaction, this surface presents no actionable security risk. (Ingestion points: post drafts and social-context.md in SKILL.md; Boundary markers: absent; Capabilities: limited to text generation; Sanitization: absent).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 07:08 AM
Security Audit — agent-trust-hub — hooks