wp-wpcli-and-ops
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute WP-CLI commands (
wp db,wp search-replace,wp plugin, etc.) and a local Node.js inspection script (wpcli_inspect.mjs) to perform site maintenance and administrative tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a potential ingestion surface for instructions embedded in site content.
- Ingestion points: The skill reads WordPress database content during
search-replaceoperations, site configuration files, andwp-cli.ymlfiles. - Boundary markers: The skill includes procedural guardrails such as dry-runs and environment confirmation, though it lacks formal technical delimiters for data processing.
- Capability inventory: The skill has the capability to execute shell commands and modify the database.
- Sanitization: There is no explicit sanitization step described for data retrieved from the database or site files before processing.
Audit Metadata