Skills
skills/shipshitdev/library/incremental-fetch/Gen Agent Trust Hub

incremental-fetch

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external APIs (such as social media platforms), which constitutes a surface for indirect prompt injection where untrusted data could influence agent behavior. \n
  • Ingestion points: references/patterns.md
  • fetch_page function processes external API responses. \n
  • Boundary markers: Absent in the provided implementation patterns. \n
  • Capability inventory: references/patterns.md
  • conn.execute (database access) and FETCH_STATE_FILE.write_text (local filesystem access). \n
  • Sanitization: Present. The Python patterns use parameterized SQL queries (? placeholders) to prevent SQL injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 01:10 PM
Security Audit — agent-trust-hub — incremental-fetch