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

postiz

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses 'npx' to download and execute the '@useclawlink/cli' package from the NPM registry. This is the official CLI tool provided by ClawLink for service integration.
  • [COMMAND_EXECUTION]: The agent is instructed to perform social media tasks by executing shell commands, including listing integrations, viewing schemas, and running posting actions.
  • [CREDENTIALS_UNSAFE]: The skill describes the storage of authentication credentials in the local '~/.clawlink/credentials.json' file, which is the standard management practice for this CLI tool.
  • [PROMPT_INJECTION]: The skill processes external data from the Postiz API (e.g., action lists and schemas), which represents a surface for indirect prompt injection. \n
  • Ingestion points: Data retrieved via 'npx @useclawlink/cli actions' and 'npx @useclawlink/cli describe' (SKILL.md). \n
  • Boundary markers: None explicitly defined. \n
  • Capability inventory: Shell command execution via 'npx @useclawlink/cli run' (SKILL.md). \n
  • Sanitization: Not specified, but the skill includes a mitigation requiring user confirmation before performing write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — postiz