synthesis
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external research notes and documents (SKILL.md). It does not specify boundary markers to isolate user data from instructions or include warnings to ignore embedded commands. However, the skill has no tool access, command execution capabilities, or network permissions, which prevents any potentially malicious data in the research notes from performing unauthorized actions. No sanitization is performed on the ingested content.
- [SAFE]: The skill consists entirely of instructional markdown and metadata. It contains no executable scripts, remote code downloads, or references to external packages.
Audit Metadata