a2ui-doc-sync-check
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and restricted to analyzing local repository files for documentation drift. It lacks capabilities for network access, file system modification, or command execution.
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection as it processes content from untrusted files in the codebase (e.g., READMEs, source code comments) to generate a report. However, the risk is negligible due to the absence of exploitable tools.
- Ingestion points: Documentation guides (
docs/), specifications,README.mdfiles, and codebase manifest files (package.json,pyproject.toml, etc.). - Boundary markers: No delimiters are used to separate ingested file content from the agent's internal instructions.
- Capability inventory: Limited to reading files and generating text reports; no high-privilege capabilities such as shell execution or external network calls are present.
- Sanitization: The skill does not perform validation or sanitization on the content extracted from audited files.
Audit Metadata