prompt-evaluator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and evaluate external prompt text, which creates an attack surface for indirect prompt injection. Malicious instructions could be embedded in the prompts being evaluated to influence the agent's behavior or bias the evaluation results.
- Ingestion points: The skill instructions for Mode 1 (Single Prompt Evaluation) and Mode 3 (Batch Evaluation) in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' directives to prevent the agent from following instructions contained within the data being analyzed.
- Capability inventory: The skill focuses on producing markdown reports and does not specify access to sensitive tools or network operations within its instructional logic.
- Sanitization: No sanitization or validation of the input prompt text is defined.
Audit Metadata