topic-advisor
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of viral breakdown reports. While this data could theoretically contain instructions to manipulate the agent, the skill is restricted to a specific JSON output schema and lacks the ability to execute code, access sensitive files, or perform network operations. Therefore, the risk is minimal.
- [SAFE]: The skill's instructions focus on maintaining factual accuracy and providing evidence for content generation. It does not include any commands for file system access, credential handling, or remote execution.
Audit Metadata