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

pandadoc

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch the @useclawlink/cli package from the npm registry.
  • [REMOTE_CODE_EXECUTION]: The skill executes the @useclawlink/cli package to perform PandaDoc operations.
  • [COMMAND_EXECUTION]: Relies on shell commands for setup (npx @useclawlink/cli login) and task execution (npx @useclawlink/cli run).
  • [PROMPT_INJECTION]: The skill processes user-supplied strings and JSON objects to execute actions.
  • Ingestion points: User-provided input for action descriptions and JSON payloads in SKILL.md.
  • Boundary markers: Not present in the command templates, though user confirmation is advised.
  • Capability inventory: Performs PandaDoc API interactions through npx subprocess calls.
  • Sanitization: The skill instructions do not specify input validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — pandadoc