to-article
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from content/TOPIC.md and content/RESEARCH.md, creating a surface for indirect prompt injection if these files contain malicious instructions.
- Ingestion points: content/TOPIC.md and content/RESEARCH.md are read during the article drafting process.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill allows writing to the file system (content/ARTICLE.md) and calculating SHA-256 integrity digests.
- Sanitization: No methods for sanitizing or validating the ingested markdown content are defined.
Audit Metadata