snap-yaml-generator

Warn

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill documentation includes build and installation commands that use administrative privileges via sudo. It specifically utilizes the --dangerous flag during snap installation, which bypasses the standard signature verification process for local packages.
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading data from a user-specified projectPath to generate configuration files. This creates a vulnerability surface where a malicious project could contain instructions designed to manipulate the agent's output or tool usage.
  • Ingestion points: Input parameters projectPath, snapName, and interfaces, as well as any files read from the local file system using Read, Glob, or Grep.
  • Boundary markers: Not present; the instructions do not specify any delimiters or safety warnings for handling untrusted file content.
  • Capability inventory: The skill utilizes Read, Write, Edit, Bash, Glob, and Grep tools to perform operations on the file system.
  • Sanitization: No evidence of content sanitization, validation, or escaping of data retrieved from the project directory before it is interpolated into the generated configuration.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 13, 2026, 08:26 PM