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

cal

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the '@useclawlink/cli' package from the public npm registry during the setup and usage phases.
  • [COMMAND_EXECUTION]: Uses 'npx @useclawlink/cli' to interact with Cal.com APIs, allowing the AI agent to read and modify calendar data via shell commands.
  • [CREDENTIALS_UNSAFE]: Mentions that the 'login' command stores authentication credentials in a local JSON file at '~/.clawlink/credentials.json'.
  • [COMMAND_EXECUTION]: The skill is susceptible to indirect prompt injection because it processes user-provided strings and external calendar data within shell commands without explicit sanitization.
  • Ingestion points: User-provided action descriptions in 'SKILL.md' and event data retrieved from external Cal.com bookings.
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are present in the command templates.
  • Capability inventory: The skill performs subprocess execution using 'npx' (File: SKILL.md).
  • Sanitization: No sanitization or validation of external input strings is documented before they are passed to the CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — cal