content-research-writer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No evidence of malicious patterns, sensitive data exposure, or prompt injection intended to bypass safety filters was found in the instructions.
- [NO_CODE]: The skill is strictly instructional and does not include any scripts, binary files, or external code dependencies.
- [PROMPT_INJECTION]: The skill processes user-supplied drafts and research topics, which is an inherent surface for indirect prompt injection. However, the agent's capabilities are limited to text processing and research, with no access to dangerous system-level operations. Ingestion points: User-provided text drafts and research topics. Boundary markers: None specified in the instructions. Capability inventory: File reading and writing, plus standard web search. Sanitization: No explicit data validation or sanitization is defined.
Audit Metadata