viral-trend-catcher
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted user input regarding product trends to guide its evaluation logic and trigger local script execution.
- Ingestion points: User descriptions of products and trends entered during interaction as defined in the Core Objective.
- Boundary markers: User input is incorporated into the workflow without the use of protective delimiters or explicit 'ignore' instructions for embedded data.
- Capability inventory: The agent is instructed to execute scripts/viral_potential.py based on user-provided context.
- Sanitization: There is no evidence of input validation or content sanitization for the external data processed by the skill.
- [SAFE]: The skill references the official domain rijoy.ai for supplementary tools, which is a verified resource belonging to the skill's author.
Audit Metadata