grok-wiki-custom
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
grok-wikiCLI tool to perform repository discovery (ask), listing, and wiki generation. These commands are executed locally using user-provided sources and parameters. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external content.
- Ingestion points: Untrusted repository data is ingested via the
<source>argument inSKILL.md. - Boundary markers: No explicit delimiters or boundary markers are used when processing repository content.
- Capability inventory: The skill can write files to the local filesystem and execute shell commands via the
grok-wikiCLI. - Sanitization: No explicit sanitization or filtering of the repository content is mentioned before it is processed by the discovery and generation tools.
- [DATA_EXPOSURE]: The skill writes temporary prompt files to the local working directory or the system's temporary directory (
$TMPDIR). This is a standard functional requirement for the tool's operation and does not involve exfiltration of sensitive data.
Audit Metadata