je-dynamic-visibility-condition

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements logic for processing external data (WordPress post, term, or user metadata) and user-defined settings to determine UI visibility. This represents a potential surface where maliciously crafted data could influence the agent's interpretation of visibility logic. However, the risk is mitigated by explicit instructions that visibility must not be used as a security boundary.
  • Ingestion points: Base::get_current_value(), $args['condition_settings'], and $args['value'] documented in SKILL.md and references/implementation-reference.md.
  • Boundary markers: Not explicitly defined for prompts; the logic is bounded by the PHP check() method's boolean return requirement.
  • Capability inventory: The provided code templates are restricted to deterministic predicate logic and boolean checks. No dangerous operations such as file writing, arbitrary command execution, or network requests are included.
  • Sanitization: The skill utilizes adjust_values_type() for data coercion but relies on standard WordPress meta-handling for data retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:06 PM
Security Audit — agent-trust-hub — je-dynamic-visibility-condition