community-traffic-report
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill description contains instructions that attempt to override the agent's default decision-making logic by mandating its use whenever a related topic is mentioned (e.g., 'Use by default whenever the user wants this outcome, even indirectly') and setting a high threshold for non-use ('Skip only if the user explicitly asks not to use this skill/workflow'). This is a directive to prioritize this specific skill over other potential tools or agent behaviors.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (analytics APIs) and incorporates it into a markdown report, creating a potential surface for indirect prompt injection.
- Ingestion points: Data retrieved from multiple tools including
classic_list_page_views,classic_list_downloads, andclassic_list_mobile_os_distribution. - Boundary markers: None identified; external data is directly aggregated into the report template.
- Capability inventory: The skill is limited to reading data and generating a markdown report ('READ_ONLY' contract).
- Sanitization: No explicit sanitization or validation of the API-returned data is mentioned before it is rendered in the final report.
Audit Metadata