exploring-signals-scouts
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on monitoring and observability within the PostHog platform, designed to help users understand the behavior of automated agents.
- [COMMAND_EXECUTION]: The skill utilizes several local Python helper scripts (e.g.,
scripts/render_run_report.py,scripts/fleet_survey.py) to process JSON data. These scripts are self-contained, use only Python standard libraries, and do not perform network operations or execute arbitrary shell commands. - [DATA_EXFILTRATION]: The skill reads project data including configuration, run logs, and SQL query results. This behavior is consistent with its primary purpose. All network operations are directed at the vendor's (PostHog) own infrastructure, and no data is exfiltrated to unauthorized third-party domains.
- [PROMPT_INJECTION]: The skill processes data from scout summaries and session logs which could theoretically contain malicious instructions (indirect prompt injection surface). However, this risk is minimal as the skill is read-only and the data is primarily processed by formatting scripts rather than being directly interpreted as instructions for the agent's core logic.
Audit Metadata