article-writing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from web searches and research notes to generate content. This creates a surface for indirect prompt injection if the source material contains malicious instructions.
- Ingestion points: The skill uses the
WebSearchtool to gather information from the internet and theReadtool to access user-provided research or notes (referenced inSKILL.md). - Boundary markers: There are no explicit instructions or delimiters provided to the agent to ignore or isolate potential instructions found within the research data or web results.
- Capability inventory: The skill is authorized to use the
Writetool for file system output and theWebSearchtool for network data retrieval (defined inSKILL.md). - Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is processed by the agent.
Audit Metadata