LLM Wiki Maintainer
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, including raw source materials and existing wiki pages, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Raw sources, wiki pages (e.g.,
wiki/index.md,wiki/log.md), andAGENTS.md(referenced inSKILL.md). - Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the ingested content.
- Capability inventory: The skill uses tools for
page writes,patch proposals, andsource reads(referenced inSKILL.md). - Sanitization: There are no instructions for sanitizing or validating the content of the source material before processing or writing it to the wiki.
Audit Metadata