skills/bedesj/k-skill/lotto-results/Gen Agent Trust Hub

lotto-results

Warn

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'k-lotto' package globally from the npm registry at runtime. Using unversioned external dependencies from non-trusted sources introduces supply chain risks.- [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage its environment, including 'npm install -g' and 'export NODE_PATH'. It also uses shell heredocs to execute embedded JavaScript snippets via 'node
  • <<'JS'', which is a form of dynamic execution of local code.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external lottery data from third-party sources.
  • Ingestion points: Data fetched from lottery results via 'lotto.getLatestRound()' and 'lotto.getDetailResult()'.
  • Boundary markers: Absent. The skill does not use delimiters or instructions to prevent the agent from obeying instructions that might be embedded in the lottery data.
  • Capability inventory: The skill has the ability to execute shell commands and Node.js code.
  • Sanitization: Absent. There is no evidence of validation or sanitization of the data retrieved from external lottery providers before it is incorporated into the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 13, 2026, 01:00 AM
Security Audit — agent-trust-hub — lotto-results