skills/yashas-30/nyx/readme/Gen Agent Trust Hub

readme

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its broad codebase exploration instructions.
  • Ingestion points: The agent is explicitly instructed to perform a 'Deep Codebase Exploration' by reading the root directory, framework configuration files (Gemfile, package.json, go.mod), database schemas, migrations, and CI/CD configurations.
  • Boundary markers: There are no instructions for the agent to use delimiters or to disregard potentially malicious natural language instructions embedded within the code, comments, or data files it reads.
  • Capability inventory: The agent has the capability to write directly to the 'README.md' file in the project root based on the information it gathers.
  • Sanitization: The skill does not implement any validation or filtering mechanisms for the content it ingests from the project files.
  • [PROMPT_INJECTION]: Potential for sensitive information exposure during the documentation process.
  • Sensitive file access: The instructions guide the agent to read highly sensitive files such as 'config/master.key', 'config/credentials.yml.enc', and '.env'. While the stated purpose is to understand the 'Credentials setup' and 'Environment Variables' for documentation, this creates a risk that the agent may inadvertently include actual secret keys or sensitive values in the public-facing 'README.md' output instead of just the variable names or structural examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 10:19 PM
Security Audit — agent-trust-hub — readme