modern-web-guidance

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the modern-web-guidance package from the NPM registry. This package is maintained by a well-known organization.- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx to perform searches and retrieve development guides.- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to command injection through unsafe interpolation of user-supplied input into shell commands.
  • Ingestion points: The <query> in the search command and the <id> in the retrieve command defined in SKILL.md.
  • Boundary markers: None are present in the command templates to prevent the interpretation of shell meta-characters.
  • Capability inventory: The skill performs shell execution and requires outbound network access to fetch the tool.
  • Sanitization: There are no instructions or mechanisms provided to validate or sanitize external input before it is used in a shell command.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 04:36 AM
Security Audit — agent-trust-hub — modern-web-guidance