doc-auto-sync
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill access sensitive file paths including
.env*files as part of its documentation mapping and synchronization logic. This constitutes data exposure of configuration files which often contain secrets. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of ingesting and processing untrusted repository data.
- Ingestion points: The skill reads the content of all files identified in
analysisContext.repo.changedFilesto map changes to documentation. - Boundary markers: No explicit delimiters or boundary markers are defined to separate untrusted source code content from the agent's internal instructions during the documentation generation process.
- Capability inventory: The skill possesses the capability to write and modify project files including
PROJECT.md,README.md,CHANGELOG.md, and other documentation files. - Sanitization: The workflow does not specify any sanitization, filtering, or validation of the content extracted from source files before it is used to generate patches.
Audit Metadata