prompt-validator
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or extract system prompts. The skill is designed to enforce structural and linguistic constraints on user prompts rather than circumventing them.
- [DATA_EXFILTRATION]: The skill does not perform any network operations (no curl, wget, or fetch) and does not reference any sensitive local file paths or environment variables. No hardcoded credentials were detected.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of external scripts. The skill relies entirely on instructional logic within the SKILL.md file.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of the prompt text to be audited. However, the capability inventory is restricted to generating text reports and rewritten prompt suggestions. The instructions explicitly command the agent NOT to execute the prompt being analyzed, which mitigates the risk of the agent obeying instructions contained within the user-provided data.
- Ingestion points: The user-provided prompt text delivered via chat input.
- Boundary markers: Absent; the skill does not specify the use of delimiters when handling the target prompt.
- Capability inventory: Limited to text generation (checklist, summary, and rewritten text).
- Sanitization: Not applicable as the skill performs no high-privilege actions based on the input.
Audit Metadata