async-learning-teacher

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The README.md file instructs users to install the skill using npx @tamng0905/builder-essential-skills. This command downloads and executes code from a package hosted on the public NPM registry under a personal scope that is not recognized as a trusted organization or well-known service.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated content processing workflow.\n
  • Ingestion points: The skill explicitly parses source URLs and fetches external web content as defined in the 'Workflow' section of SKILL.md.\n
  • Boundary markers: There are no instructions to use delimiters or ignore instructions found within the fetched source material, which could allow an attacker to embed malicious prompts in a web page that the agent then obeys.\n
  • Capability inventory: The agent is granted capabilities to fetch network data and write the resulting 'teaching artifacts' directly to the user's filesystem, notes apps, or knowledge bases.\n
  • Sanitization: The skill lacks any requirement for the agent to sanitize, validate, or filter the external content before processing or saving it to persistent storage.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 03:29 PM
Security Audit — agent-trust-hub — async-learning-teacher