skills/clawlink-hq/skills/contentful/Gen Agent Trust Hub

contentful

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx @useclawlink/cli, which fetches and executes the CLI tool from the public npm registry at runtime.
  • [COMMAND_EXECUTION]: The skill relies on shell commands to manage authentication and execute Contentful actions via the ClawLink CLI.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: SKILL.md (via actions like contentful_get_content_types, contentful_get_asset, and contentful_get_editor_interface which read data from external Contentful environments).
  • Boundary markers: Absent; there are no specific instructions or delimiters to isolate data fetched from Contentful from the agent's primary instruction set.
  • Capability inventory: SKILL.md (via the npx @useclawlink/cli run contentful command which allows the agent to execute write actions and updates in Contentful).
  • Sanitization: Absent; the skill does not specify any validation or sanitization for the content retrieved from external environments before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — contentful