content-production
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided topics and draft files, which is a standard operational requirement for content production but represents a potential surface for indirect prompt injection.\n
- Ingestion points: Reads content from
.claude/product-marketing-context.mdand user-provided drafts inSKILL.md.\n - Boundary markers: No explicit delimiters or instructions are used to separate ingested content from the agent's core instructions.\n
- Capability inventory: Uses local Python scripts (
seo_optimizer.py,content_scorer.py,brand_voice_analyzer.py,content_quality_gates.py) for file-based analysis.\n - Sanitization: No content sanitization is performed prior to processing by the agent or analysis tools.
Audit Metadata