clawdbot-cost-tracker
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [Data Exposure] (MEDIUM): Path Traversal in
scripts/calculate-cost.js. The script uses the second command-line argument (process.argv[2]) to construct a file path viapath.join. An attacker could pass a relative path (e.g.,../../target) to read unintended files ending in.json. - [Indirect Prompt Injection] (MEDIUM): The skill handles untrusted data from session metadata. Ingestion points:
stdininsnapshot-usage.jsandargvin both scripts. Boundary markers: None. Capability inventory: File system read/write viafsmodule. Sanitization: None; inputs are used directly in file paths and content. - [Command Execution] (LOW): Core functionality is implemented through local Node.js scripts. While these are part of the skill, they provide the agent with broad file system access without sufficient input validation.
Audit Metadata