autopilot-status
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script named
campaign-health-monitor.pywith subcommandshealth-score,corrections-history, andsavings-reportto gather dashboard information. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of local data.
- Ingestion points: Reads brand context and agency SOPs from
~/.claude-marketing/brands/and~/.claude-marketing/sops/. - Boundary markers: There are no markers or instructions provided to the agent to ignore potentially malicious instructions within these files.
- Capability inventory: The skill has the ability to execute the
campaign-health-monitor.pyscript based on gathered data. - Sanitization: The skill does not implement sanitization or validation of the content read from the local marketing files.
Audit Metadata