add-evm-network
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and adhere to a 'single source of truth' document (
docs/add-evm-swaps-bridge-network.md) within the repository. This pattern introduces a surface where malicious instructions embedded in that document could override the skill's primary logic. - Ingestion points:
docs/add-evm-swaps-bridge-network.md(repos/metamask-extension.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts in the source document.
- Capability inventory: The agent is permitted to modify source code, update
package.jsondependencies, and run test suites. - Sanitization: No sanitization or validation of the document content is performed before processing.
- [SAFE]: All external references, such as GitHub pull request links and the
@metamask/bridge-controllerdependency, are official resources belonging to the vendor.
Audit Metadata