skills/ruvnet/claude-flow/cost-export/Gen Agent Trust Hub

cost-export

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script located at plugins/ruflo-cost-tracker/scripts/export.mjs using the Bash tool to process and format telemetry data.
  • [DATA_EXFILTRATION]: The skill's primary function is to transmit internal telemetry data, including session identifiers and budget configurations, to external destinations via HTTP POST requests (webhooks) or local filesystem writes (Prometheus textfiles) as directed by command arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential attack surface by ingesting internal session data and providing network and filesystem write capabilities. 1. Ingestion points: The skill reads session-* and budget-config-* records from the cost-tracking namespace in AgentDB. 2. Boundary markers: No delimiters or ignore-embedded-instruction warnings are present in the instruction set. 3. Capability inventory: The skill has the capability to write to the filesystem (via --prometheus) and perform network POST requests (via --webhook). 4. Sanitization: The instructions do not specify sanitization or validation logic for the telemetry data being exported.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:23 PM
Security Audit — agent-trust-hub — cost-export