NYC

cost-verification-auditor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill identifies a surface for indirect prompt injection because it is designed to ingest and process untrusted user data for token estimation. Ingestion points: User prompts and source code snippets are processed in the calibration logic described in SKILL.md. Boundary markers: There are no instructions or delimiters suggested to isolate the ingested content from agent instructions. Capability inventory: The skill manifest authorizes the use of 'Bash', 'Read', and 'Write' tools. Sanitization: No sanitization or escaping of the processed text data is indicated in the guidelines.
  • [No Code] (SAFE): The skill consists entirely of markdown documentation and reference data without any executable scripts or binary files, minimizing the risk of direct malicious execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM