dpa-review
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely within the scope of its intended purpose as a legal review assistant. It reads its own configuration and playbook files from a localized directory (
~/.claude/plugins/config/claude-for-legal/) and writes results to a structured matter-specific folder. These operations are standard for a document-processing agent. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and analyze untrusted external documents such as DPAs provided via files, links, or pasted text.
- Ingestion points: Processes user-provided PDF files, Google Drive links, and pasted document text as described in the
argument-hint. - Boundary markers: There are no explicit instructions or delimiters (such as XML tags or triple quotes) defined to encapsulate the ingested DPA content within the review workflow.
- Capability inventory: The skill has read access to its configuration playbooks and write access to specific output directories for review memos. It is also instructed to use legal research and web search tools.
- Sanitization: The instructions do not specify any validation, filtering, or sanitization of the external content before it is processed by the agent.
Audit Metadata