technical-writing
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to fetch and analyze content from external, untrusted URLs.
- Ingestion points: Untrusted data enters the agent context via
web_fetchorweb_searchtools in Phase 2 ofSKILL.md. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when processing the retrieved content.
- Capability inventory: The skill uses
web_fetch,web_search, and file-writing capabilities viapresent_files. - Sanitization: No evidence of input validation, sanitization, or filtering of the external content before processing was found.
Audit Metadata