yaml-master
Execute proactive YAML intelligence: automatically activates when working with YAML files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires outputting "Corrected YAML with minimal diffs" (and follow-up commands) without any redaction guidance, so if input YAML contains secrets the LLM would likely reproduce them verbatim, creating an exfiltration risk.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill’s required runtime workflow ingests the user’s YAML file contents by design (it “reads the YAML file” to parse/validate and generate minimal edits), so any outsider-authored text can become the agent’s input when they supply or edit those YAML files.
- Commit
88dcf65
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.