wp-wpcli-and-ops
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a utility script
scripts/wpcli_inspect.mjsthat executes the system'swpbinary usingnode:child_process. This is intended to inspect the WordPress site's path, version, and configuration to ensure correct targeting before destructive operations are performed.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from the WordPress database via WP-CLI commands.\n - Ingestion points: The script
scripts/wpcli_inspect.mjscaptures the output of commands likewp option get siteurlandwp core versioninSKILL.md.\n - Boundary markers: The inspection results are returned to the agent in a structured JSON format.\n
- Capability inventory: The skill facilitates extensive file system and database write operations through
wpcommand execution.\n - Sanitization: Data retrieved from the site is passed as strings within a JSON object; the skill relies on the agent's ability to distinguish data from instructions.
Audit Metadata