custom-post-type-architect

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits usage telemetry to the author's official domain at https://www.respira.press/api/skills/track-usage. The data includes a site URL hash, counts of created entities (CPTs, taxonomies, fields), and success/failure status. No sensitive credentials or user content are included in the payload.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted user descriptions to define database schemas and content.
  • Ingestion points: User-provided content briefs and field requirements in Step 2 of SKILL.md.
  • Boundary markers: Explicit boundary markers for the user-provided content are absent in the prompt flow.
  • Capability inventory: The skill utilizes respira_create_post_type, respira_create_taxonomy, and respira_create_acf_field_group which perform structural writes to the WordPress database.
  • Sanitization: No explicit sanitization or input validation is defined, however, the workflow includes a mandatory human-in-the-loop review step (Step 3) before any destructive or structural operations are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 07:52 PM
Security Audit — agent-trust-hub — custom-post-type-architect