skills/kriscard/skills/tweet-today/Gen Agent Trust Hub

tweet-today

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the agent's context and defined workflow to generate text drafts. It does not perform any network operations, external downloads, or command execution.
  • [SAFE]: Step 3 (Safety Gate) explicitly instructs the agent to scan sources and remove/generalize sensitive data such as secrets, credentials, tokens, and private URLs, replacing them with placeholders like YOUR_API_KEY.
  • [SAFE]: The skill uses disable-model-invocation: true in its frontmatter, ensuring it acts as a set of instructions for the agent rather than executing external tools autonomously.
  • [SAFE]: File access is restricted to reading a local reference file (references/twitter-voice.md) and optionally appending a draft to a specific project file (`1
  • Projects/Public Technical Presence/Public Technical Presence.md`) only upon explicit user approval.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 04:51 PM
Security Audit — agent-trust-hub — tweet-today