write-seo-geo-content

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by design, as it must ingest and process untrusted external data to fulfill its research requirements.
  • Ingestion points: External data is collected through web searches for statistics (SKILL.md, Step 4) and via user-provided reference documents (SKILL.md, Step 1).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the external research data.
  • Capability inventory: The agent is authorized to read local files, perform web searches, and write markdown articles to specific workspace folders.
  • Sanitization: No explicit sanitization, validation, or escaping of external content is specified before the data is integrated into the writing process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 05:41 PM