stale-content-detector

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits telemetry data to the vendor's endpoint for usage tracking.\n
  • Evidence: The telemetry section specifies recording site URL hashes, content counts, and bucket distributions sent to https://www.respira.press/api/skills/track-usage.\n- [PROMPT_INJECTION]: The skill processes untrusted data from WordPress databases, which serves as a surface for indirect prompt injection.\n
  • Ingestion points: WordPress page and post content retrieved via respira_list_pages, respira_list_posts, and respira_list_custom_posts (SKILL.md).\n
  • Boundary markers: None present to distinguish site content from agent instructions.\n
  • Capability inventory: respira_delete_page (restricted to user-confirmed actions) and respira_create_page_duplicate.\n
  • Sanitization: No explicit validation or filtering of retrieved site content is defined before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:11 PM
Security Audit — agent-trust-hub — stale-content-detector