query
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'llm-wiki' command-line tool to perform search and synchronization tasks within the wiki vault environment. These actions are consistent with the skill's stated purpose of managing a knowledge base.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from a wiki vault which could contain instructions intended to influence the agent's behavior. * Ingestion points: The skill reads from the 'wiki/' directory and configuration files like 'wiki-purpose.md' via the 'llm-wiki search' command. * Boundary markers: No specific delimiters are defined in the instructions to isolate retrieved content from the agent's system prompts. * Capability inventory: The skill has the capability to search the wiki, read arbitrary pages, create new markdown pages, and update the 'wiki-log.md' file. * Sanitization: There are no explicit instructions to sanitize or validate the content retrieved from the wiki vault before it is used for synthesis.
Audit Metadata