second-brain-lint
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-curated markdown files to analyze wiki integrity, which introduces a potential indirect prompt injection surface if the content within the wiki pages originates from untrusted sources.
- Ingestion points: Local markdown files under the
wiki/directory structure, includingwiki/sources/,wiki/entities/,wiki/concepts/, andwiki/synthesis/. - Boundary markers: Absent. There are no explicit instructions or structural delimiters specified to handle malicious instructions embedded within the wiki files.
- Capability inventory: Uses the
Bashtool to run local text processing commands (grepandsort), and usesWriteandEdittools to update files such aswiki/log.md. - Sanitization: Absent. The content from the files is read and processed directly as text data without validation or structural escaping.
Audit Metadata