ai-tech-summary

Warn

Audited by Snyk on Feb 24, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill ingests third‑party RSS entries/fulltext from the SQLite tables (feeds, entries, and optional entry_content) produced by ai-tech-rss-fetch and its scripts/time_report.py, and SKILL.md / references/report-format.md explicitly tell the agent to treat those records as primary evidence for RAG summarization, so arbitrary web-provided content could contain instructions that materially influence agent outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 03:03 PM