validate-integration-docs
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the 'vale' linter and 'elastic-package' CLI tools to check documentation quality and build packages. These are standard development tools within the Elastic ecosystem.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it processes content from external markdown files to generate edit proposals. A malicious file could attempt to manipulate the agent's logic during the review process.
- Ingestion points: Markdown source files located in '_dev/build/docs/' and 'packages/*/docs/'.
- Boundary markers: The skill does not define specific delimiters to separate untrusted document content from instruction context.
- Capability inventory: The skill can execute local commands ('vale', 'elastic-package') and perform file system writes via the Edit tool.
- Sanitization: The skill enforces a mandatory human confirmation step ('Confirm before editing') before any changes are applied to the source files, which acts as a critical safeguard against automated exploitation.
Audit Metadata