skills/autoagc/linkpix-skills/linkpix/Gen Agent Trust Hub

linkpix

Fail

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches Node.js binaries and CLI tools from well-known repositories such as nodejs.org and the npm registry. It also provides fallbacks to established mirror services like Alibaba's npmmirror.
  • [COMMAND_EXECUTION]: It executes multiple shell commands for environment preparation, including extraction of archives, package installation via npm, and integrity verification using checksums.
  • [PERSISTENCE]: The setup instructions include steps to modify the user's shell configuration file ('~/.bashrc') to persistently add local binary paths to the system environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill features capabilities like 'video-inspire' that ingest data from external sources (e.g., Douyin or TikTok video links). This creates a potential attack surface where malicious instructions could be embedded in the external content. -- Ingestion points: 'resourceUrl' and 'playVideo' parameters in SKILL.md. -- Boundary markers: No delimiters or explicit instructions were found to isolate the external content. -- Capability inventory: The skill has the ability to execute CLI tools and potentially run shell commands for image/video processing. -- Sanitization: No specific sanitization or filtering logic is mentioned for the content retrieved from external URLs.
Recommendations
  • HIGH: Downloads and executes remote code from: https://nodejs.org/dist/v22.22.3/SHASUMS256.txt - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 1, 2026, 03:58 PM