social-analytics-report
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the AI agent to follow when analyzing data. It does not include any scripts, binaries, or command-line instructions.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The instructions specifically forbid the agent from claiming access to external systems like ad accounts or native analytics.
- [PROMPT_INJECTION]: The instructions do not contain bypass markers or attempts to override safety filters. On the contrary, the skill includes hard rules to prevent the fabrication of data and maintain honesty in reporting.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or packages.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external performance metrics provided by the user. While this represents a data ingestion surface, the skill lacks any dangerous capabilities (such as shell access, file writes, or network calls) that could be exploited through malicious data. It also explicitly instructs the agent to label the data boundary and separate raw observations from interpretation.
Audit Metadata