wordpress-deep-audit
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the target WordPress installation, which could be used for indirect prompt injection attacks.
- Ingestion points:
scripts/collect-system-info.shretrieves lists of plugins, themes, and cron events using WP-CLI. - Boundary markers: Output from the scripts is not delimited by specific markers to protect the agent against potentially embedded instructions in plugin names or event hooks.
- Capability inventory: The provided scripts are restricted to read-only operations via WP-CLI and do not perform file writes, modifications, or network requests.
- Sanitization: There is no evidence of sanitization or escaping of the metadata retrieved from the site components before it is presented to the agent context.
Audit Metadata