patent-review
Warn
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
Prerequisitessection instructs the agent/user to configure a custom MCP server by executing a local Python script:python3 "$HOME/aris_repo/mcp-servers/codex-exec/server.py". This relies on the security of the locally clonedaris_repoand grants the MCP server the ability to execute code. - [DATA_EXFILTRATION]: The skill's primary function involves reading sensitive, potentially trade-secret patent documents (claims, invention disclosures, and specifications) and transmitting them to an external model (
gpt-6-astra) via themcp__codex__codextool. This presents a risk of intellectual property exposure to a third-party service. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits a significant vulnerability surface for indirect prompt injection. It ingests data from untrusted external patent files and interpolates it into a high-reasoning prompt. The agent is then instructed to "Implement Fixes" (using
WriteandEdittools) based on the model's output, allowing malicious instructions embedded in a patent file to potentially trigger unauthorized file system modifications. - Ingestion points:
patent/CLAIMS.md,patent/specification/,patent/figures/numeral_index.md,patent/PRIOR_ART_REPORT.md, andpatent/INVENTION_DISCLOSURE.md. - Boundary markers: The skill uses structural headers like
CLAIMS:but lacks explicit delimiters or instructions to the model to disregard instructions contained within the ingested text. - Capability inventory: The agent uses
Bash,Read,Write, andEdittools to process the review and modify the application files. - Sanitization: No sanitization, validation, or escaping of the ingested patent text is performed before it is sent to the LLM.
Audit Metadata