prompt-improver

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (SAFE): The instructions follow a standard operational procedure and do not contain attempts to bypass safety filters or ignore system instructions.
  • [Data Exposure & Exfiltration] (SAFE): The skill utilizes tools like Grep, Git Log, and WebFetch for contextual research. There is no evidence of hardcoded credentials or attempts to exfiltrate sensitive files to unauthorized external domains.
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest data from external web sources and local project files to influence its decision-making and question-generation phases. This introduces a vulnerability surface where an attacker could place malicious instructions in a webpage or file to manipulate the agent's output.
  • Ingestion points: WebSearch, WebFetch, Grep/Glob (SKILL.md).
  • Boundary markers: No specific delimiters or safety warnings for external content are defined in the workflow.
  • Capability inventory: TodoWrite, Grep, Git Log, WebSearch, WebFetch (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the ingested content is described before it is used to generate questions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM