process-scope-statistics

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/run-process-scope-statistics.mjs captures raw command-line arguments and passes them to runTiangongCommand. This creates a potential surface for command injection if the underlying execution engine uses a shell and the agent passes un-sanitized user input into the arguments.
  • [DATA_EXFILTRATION]: The skill is designed to access sensitive configuration data by reading .env files and environment variables prefixed with TIANGONG_LCA_*. While this is standard for the tool's operation, it involves the handling of credentials or tokens.
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by fetching and processing remote data from the TianGong LCA platform.
  • Ingestion points: Remote process rows are fetched and stored in inputs/processes.snapshot.rows.jsonl by the CLI.
  • Boundary markers: There are no explicit instructions or delimiters in the markdown reports to prevent the agent from following instructions embedded within the data rows.
  • Capability inventory: The skill possesses command execution capabilities through the runTiangongCommand function in scripts/run-process-scope-statistics.mjs.
  • Sanitization: No sanitization or filtering of the remote data is performed before it is summarized into reports for the agent's consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:57 AM
Security Audit — agent-trust-hub — process-scope-statistics