cspell

Warn

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill frequently invokes npx cspell in references/config-bootstrapping.md, which downloads and executes the cspell package from the npm registry if not already present. The streetsidesoftware organization is not listed as a Trusted External Source.
  • REMOTE_CODE_EXECUTION (MEDIUM): The use of npx to execute a third-party package (cspell) constitutes remote code execution. This is used for initialization (npx cspell init) and verification (npx cspell --no-progress).
  • COMMAND_EXECUTION (LOW): The skill executes multiple shell commands including cspell --version and npx cspell init. These commands are used to manage project spell-checking state and verify installations.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection as it processes untrusted source code and configuration files to identify spelling errors.
  • Ingestion points: Project source files and configuration files (e.g., package.json, cspell.json) searched in SKILL.md (Workflow Step 1).
  • Boundary markers: None identified; the skill directly processes content from files.
  • Capability inventory: Execution of npx cspell commands and filesystem write operations for configuration updates and inline directives.
  • Sanitization: None; words extracted from source code are used to suggest modifications or update dictionaries.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 04:23 PM