automated-content-generation
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The 'AI FIRST Quality Principle' section uses high-pressure, mandatory language ("MUST", "ALL", "NEVER", "NO SHORTCUTS") to override the agent's default response patterns. It explicitly commands the agent to disregard single-pass quality and forces a minimum of two complete iterations for all analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest structured data and external information for automated news and intelligence report generation, creating a surface for indirect instructions.
- Ingestion points: Reads external data for template-based content generation (SKILL.md).
- Boundary markers: Mentions 'Content validation' but does not define specific technical delimiters (e.g., XML tags or clear boundaries) to separate data from instructions.
- Capability inventory: No direct subprocess or file-write operations are present in SKILL.md itself, though the skill is designed to integrate with GitHub workflows.
- Sanitization: Mentions 'validation' and quality checks as part of the iteration process, though these are AI-driven rather than programmatic sanitization.
Audit Metadata