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

tinypng

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and run the @useclawlink/cli package from the NPM registry. This is the official tool provided by the vendor (ClawLink) for interacting with their service.
  • [COMMAND_EXECUTION]: The skill relies on shell commands to perform setup and execution tasks. It uses npx @useclawlink/cli login for authentication and various run commands to perform TinyPNG operations like image shrinking and transformation.
  • [PROMPT_INJECTION]: The skill processes data retrieved from the TinyPNG API (e.g., compression counts, image IDs), which constitutes an indirect prompt injection surface. The instructions include a safeguard requiring the agent to confirm with the user before performing any write operations.
  • [DATA_EXPOSURE]: The documentation identifies that credentials for the service are stored locally at ~/.clawlink/credentials.json. The skill describes this as part of the standard setup process and does not include instructions to exfiltrate or unsafely access this file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — tinypng