Modcaster Expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill contains only high-level architectural documentation and feature descriptions for a podcast application; no scripts, commands, or executable code are present.
- [SAFE] (SAFE): No security threats such as obfuscation, credential leaks, or exfiltration patterns were detected.
- [Indirect Prompt Injection] (LOW): The skill involves ingesting external RSS feeds, which represents an attack surface for indirect prompt injection. 1. Ingestion points: RSS feed data extraction (SKILL.md). 2. Boundary markers: None specified. 3. Capability inventory: Allowed tools include Read, Edit, and Grep. 4. Sanitization: Documentation mentions handling malformed feeds gracefully but provides no LLM-specific security sanitization guidelines.
Audit Metadata