korean-slang-writing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches slang definitions and summaries from
namu.wiki. It also usesnpxto download the vendor-owned CLI package@nomadamas/k-skillfrom the NPM registry to provide instructions and execute scripts. - [COMMAND_EXECUTION]: The skill utilizes
npxto execute its CLI tool for managing updates, retrieving instructions, and running Python helper scripts (slang_search.pyandslang_lookup.py). - [INDIRECT_PROMPT_INJECTION]: The skill processes content from Namu Wiki, a community-edited platform. This creates an attack surface where an adversary could edit a wiki page to include malicious instructions that the agent might follow when summarizing the slang terms.
- Ingestion points:
scripts/slang_lookup.pyfetches HTML content from external URLs onnamu.wiki. - Boundary markers: The skill instructions do not define specific delimiters or "ignore embedded instructions" warnings for the fetched wiki content.
- Capability inventory: The skill possesses network access (restricted to Namu Wiki) and file system read access for local JSON indices.
- Sanitization: While
scripts/slang_lookup.pyremoves<script>,<style>, and other HTML tags using regular expressions, it does not sanitize the resulting text for natural language injection patterns.
Audit Metadata