The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to download and install the ecc-agentshield package from the npm registry using npm install -g ecc-agentshield.- [REMOTE_CODE_EXECUTION]: The skill utilizes npx to execute code directly from the npm registry (npx ecc-agentshield scan). This involves fetching and running scripts from a remote source on the user's machine.- [COMMAND_EXECUTION]: The skill provides numerous shell commands for the agent to execute, including scanning directories, initializing configurations, and applying 'auto-fixes' to project files.- [REMOTE_CODE_EXECUTION]: The skill is designed to ingest and process untrusted local configuration data from files like .claude/settings.json, CLAUDE.md, and mcp.json. While it functions as a security scanner, the ingestion of these files constitutes an attack surface for indirect prompt injection if the files contain malicious instructions.
Ingestion points: .claude/settings.json, CLAUDE.md, mcp.json, hooks/*.md, agents/*.md
Boundary markers: None specified in the instructions.
Capability inventory: Shell command execution via npx, npm install, and file system access.
Sanitization: No explicit sanitization or validation of the processed files is described in the skill.

security-scan