developer-growth-analysis
Warn
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill reads the
~/.claude/history.jsonlfile, which contains sensitive user interaction data, project names, and pasted code snippets. This information is summarized and transmitted to an external Slack workspace via Rube MCP tools. While intended for personalized reporting, this pattern involves reading highly sensitive local data and sending it to a remote service, which could be exploited for exfiltration. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted historical data from chat logs. Ingestion points: Data is ingested from
~/.claude/history.jsonl(fields:display,pastedContents). Boundary markers: No delimiters or instructions to ignore embedded commands are present to separate the data from the analysis logic. Capability inventory: The agent usesRUBE_SEARCH_TOOLS,RUBE_MANAGE_CONNECTIONS, andRUBE_MULTI_EXECUTE_TOOLto interact with HackerNews and Slack. Sanitization: There is no evidence of sanitization or filtering of the historical chat content before it is processed.
Audit Metadata