maa-wiki
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch and process Markdown content from an external GitHub repository hosted by a third-party user (
Windsland52/MaaLLMWiki). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documentation and schema files from a remote source, which could be used to deliver malicious instructions to the agent.
- Ingestion points: Markdown files retrieved from
https://raw.githubusercontent.com/Windsland52/MaaLLMWiki/main/as described inSKILL.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded within the fetched documentation.
- Capability inventory: The analyzed files (
SKILL.md,agents/openai.yaml) primarily focus on information retrieval and navigation; no specific command execution or file system modification scripts are included in this skill package. - Sanitization: Absent. The content is retrieved and used directly by the agent without validation or filtering.
Audit Metadata