yaml-master

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to automatically ingest and process untrusted YAML configuration files from the user's workspace.
  • Ingestion points: Automatically triggers on and reads .yaml and .yml files as described in SKILL.md and references/SKILL.full.md.
  • Boundary markers: The instructions do not define clear delimiters or instructions for the agent to treat file content strictly as data, increasing the risk that the agent might follow instructions embedded within a YAML file.
  • Capability inventory: The skill has access to powerful tools including Read, Write, Edit, and Bash, which could be abused if an injection is successful.
  • Sanitization: There is no explicit logic described for sanitizing or escaping the content of the YAML files before processing.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute or suggest validation commands for YAML configurations, such as kubectl or Docker Compose checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:53 PM