writing-helper
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill consists only of a Markdown file providing persona instructions. No Python, Node.js, or shell scripts are present.
- [PROMPT_INJECTION]: The skill accepts user input for text processing, creating a surface for indirect prompt injection. However, the risk is minimal as the skill lacks code-based capabilities like network or file access. * Ingestion points: User-provided text segments in SKILL.md. * Boundary markers: No delimiters or ignore instructions provided for user input. * Capability inventory: No subprocess calls or network operations detected in SKILL.md. * Sanitization: No sanitization of external content is specified.
Audit Metadata