The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using npm and npx to conduct dependency security audits and apply fixes. It also includes an MCP tool call to dispatch background audit tasks.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @claude-flow/cli package from the npm registry. This is a standard method for running the utility without permanent installation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from project dependency files and external audit results.
Ingestion points: Local package configuration files and JSON audit output.
Boundary markers: None provided in the instructions.
Capability inventory: Subprocess execution via Bash tool and execution of MCP tool mcp__claude-flow__hooks_worker-dispatch.
Sanitization: No sanitization or validation of the input data is described.

dependency-check