pdf-brain
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
joelclawcommand-line utility to execute search and retrieval operations against a document corpus. - Evidence: Workflow steps involve running
joelclaw docs searchandjoelclaw docs contextto find information. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing content from external PDF documents and using that content to generate system configuration advice and shell commands.
- Ingestion points: Document content is retrieved via the
joelclawsearch tool inSKILL.md. - Boundary markers: None explicitly defined to separate untrusted document content from the agent's instructions.
- Capability inventory: The skill is designed to produce Kubernetes implementation paths and verification commands based on the retrieved documentation.
- Sanitization: No specific filtering or validation of the retrieved text is mentioned prior to synthesis.
Audit Metadata