national-pension-workplace
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to use
npx -y @nomadamas/k-skill@0. This downloads and executes a CLI utility from the NPM registry managed by the skill's author. - [COMMAND_EXECUTION]: The skill relies on shell commands to interact with its helper script and the author's management CLI to fetch up-to-date instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes workplace coverage data fetched from an external proxy, which constitutes a potential surface for instructions embedded in external data records.
- Ingestion points: The
scripts/national_pension_workplace.pyfile fetches JSON payloads from thek-skill-proxyendpoint. - Boundary markers: There are no explicit delimiters used in the helper script to mark data boundaries for the agent.
- Capability inventory: The skill performs network operations using
urllib.requestto communicate with the proxy service. - Sanitization: Data is parsed using standard
json.loadswithout additional sanitization or filtering of the content fields before processing.
Audit Metadata