professional-proofreader
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing untrusted data.
- Ingestion points: Processes user-provided inline text and uploaded document files such as .docx, .txt, and .pdf as specified in SKILL.md and its references.
- Boundary markers: The instructions do not define delimiters or provide 'ignore embedded instructions' warnings when processing user content.
- Capability inventory: The skill has permissions to read source documents and write updated files to the local environment.
- Sanitization: No evidence of content sanitization or validation of ingested text is present.
Audit Metadata