keyword-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process arbitrary user-provided text for the purpose of keyword extraction, creating a potential surface for indirect instructions.
- Ingestion points: Processes user-supplied text paragraphs and content in Step 1 — Analyze and Step 2 — Generate Keywords.
- Boundary markers: No specific delimiters or instructions are provided to the agent to treat input text strictly as data or to ignore embedded instructions.
- Capability inventory: The skill has no access to tools, shell commands, file writing, or network operations.
- Sanitization: No input validation or sanitization logic is present to filter malicious instructions within the processed text.
Audit Metadata