exploring-signals-scouts

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill utilizes tools to read scout configurations, run logs, and durable memory (scratchpad). It also provides a SQL query for the document_embeddings table to track emitted signals. These operations are consistent with the skill's purpose as a PostHog observability tool and are restricted to the vendor's data environment.
  • [COMMAND_EXECUTION]: The skill includes four Python scripts (assess_health.py, emitted_signals.py, fleet_survey.py, render_run_report.py) used for data formatting. These scripts are standalone, use only the Python standard library, and do not perform network I/O or execute external shell commands.
  • [PROMPT_INJECTION]: As an exploratory tool, the skill processes run logs and scratchpad entries which may contain content generated by other AI agents. This represents an indirect prompt injection surface; however, the skill is strictly read-only and intended for human-in-the-loop diagnostic workflows, mitigating the risk of automated instruction following from processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:35 PM
Security Audit — agent-trust-hub — exploring-signals-scouts