measuring-social-performance
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from social media platforms, which may contain attacker-controlled content.
- Ingestion points: The skill explicitly requests "access to your current social media analytics dashboards" (Question 4) and suggests users provide "exported data files (e.g., CSVs from your analytics platforms)" for quantitative analysis.
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious embedded instructions within the ingested performance data or user-generated content (e.g., comments or social media posts included in the data exports).
- Capability inventory: The skill's primary capabilities involve data analysis, performance modeling, and report generation. There are no high-privilege tools (such as arbitrary command execution or network writing) visible in the provided content.
- Sanitization: There are no documented mechanisms for sanitizing, escaping, or validating the external content before it is processed by the agent.
Audit Metadata