gingiris-twitter-agent-ops

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional documentation, templates, and metadata. It does not contain any executable scripts, binary files, or automated commands that perform sensitive system or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill's core workflow involves processing external data (such as blog posts, social media content, and interview transcripts) to generate social media posts. This creates a potential surface for indirect prompt injection if the ingested material contains malicious instructions designed to hijack the agent's behavior.
  • Ingestion points: Construction of the SOURCE-INDEX using external articles, podcasts, and interview transcripts (referenced in SKILL.md and README.md).
  • Boundary markers: The skill includes 'Hard Rules' and a 'Pre-publish QC' checklist to serve as logical guardrails.
  • Capability inventory: The agent is instructed to draft and schedule social media content based on the provided data.
  • Sanitization: Relies on 'Triple Translation' checks and manual quality control reviews rather than programmatic filtering of input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 02:31 AM
Security Audit — agent-trust-hub — gingiris-twitter-agent-ops