wiki-rebuild
Warn
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via a CLI tool, falling back to
qmdif theQMD_CLIenvironment variable is unset. It performs operations such asupdate,embed,ls, andget. This represents a risk if the environment variable or paths are manipulated. - [INDIRECT_PROMPT_INJECTION]: The skill employs a 'Config Resolution Protocol' that searches parent directories for
.envfiles. This creates a significant vulnerability surface. - Ingestion points: The agent reads
.envfiles from arbitrary parent directories based on the current working directory. - Boundary markers: The skill relies on user confirmation for destructive actions but lacks technical validation for the configuration values loaded from external files.
- Capability inventory: The skill can delete all content in category directories (
concepts/,entities/, etc.), remove the.manifest.jsonfile, and execute shell commands. - Sanitization: There is no evidence of path validation or shell argument escaping for the
QMD_CLIcommand or the$QMD_WIKI_COLLECTIONvariable. - [COMMAND_EXECUTION]: The skill includes instructions to 'Clear live wiki,' which involves removing all content from multiple directories. While this is an intended feature, the lack of path sanitization makes it a high-risk capability that could be misdirected to delete system files if
OBSIDIAN_VAULT_PATHis poisoned. - [DATA_EXFILTRATION]: The skill explicitly instructs the agent to read
.envfiles and the.manifest.jsonfile. While intended for configuration, these files often contain sensitive metadata or secrets, and the automated resolution process increases the risk of unauthorized data access.
Audit Metadata