english-prompt-review
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices by requiring the redaction of sensitive credentials, such as API keys, tokens, and passwords, replacing them with stable placeholders to prevent accidental exposure in outputs.
- [SAFE]: The instructions establish a clear privacy boundary by forbidding the transmission of prompt data to external services for analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user prompts as input for coaching. Ingestion points: User prompts ingested in SKILL.md. Boundary markers: Output is confined to a specific markdown section to separate coaching from task results. Capability inventory: The skill is a text-transformation utility and does not invoke external tools or network operations. Sanitization: Credential redaction is performed prior to processing to mitigate data exposure risks.
Audit Metadata