writing-quality
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-supplied data described as 'Draft text to improve'.
- Ingestion points: User-provided drafts enter the agent's context as defined in the 'Required Inputs' section of
SKILL.md. - Boundary markers: The instructions do not define explicit delimiters or boundary markers to separate the untrusted user input from the skill's internal instructions, which could allow maliciously crafted input to influence agent behavior.
- Capability inventory: The skill's capabilities are restricted to text analysis and generation; no scripts, network operations, or privileged file access commands are present in the skill package.
- Sanitization: There are no built-in mechanisms described to sanitize or escape user-provided text before processing.
Audit Metadata