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), and AGENTS.md (referenced in SKILL.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, and source reads (referenced in SKILL.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
Risk Level
SAFE
Analyzed
Oct 31, 2026, 11:29 PM