ai-newsletters

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes content from third-party RSS feeds (TLDR AI and The Rundown AI) which may contain malicious instructions designed to manipulate the agent.
  • Ingestion points: RSS feed content (titles, links, descriptions) extracted via WebFetch in SKILL.md (Workflow Step 2).
  • Boundary markers: Absent. The skill does not use specific delimiters or instructions to prevent the agent from obeying commands embedded in the feed content during the ranking or summarization process.
  • Capability inventory: File-write access to the local filesystem (50_资源/Newsletters/) for saving digests and raw data as defined in SKILL.md (Workflow Step 6).
  • Sanitization: Absent. There is no evidence of filtering or sanitizing the input strings before they are processed by the LLM for ranking or template filling.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM