verify-protocol

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests installing components from the vendor's repository using the command npx skills add wellgent/skills -s verify-protocol.
  • [COMMAND_EXECUTION]: The provided dev-server.sh script template manages the lifecycle of local development servers using process management utilities such as kill and lsof, and interacts with local endpoints via curl to verify server status.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a verification protocol that ingests instructions from multiple sources to guide agent behavior.
  • Ingestion points: The agent is instructed to read shared mechanics from verify-protocol.md and repository-specific implementation details from a project-local verify skill.
  • Boundary markers: The templates do not define explicit delimiters or instructions for the agent to ignore potentially adversarial content within the project-specific sections.
  • Capability inventory: The protocol grants the agent the ability to execute the dev-server.sh shell script and interact with the application via the agent-browser tool.
  • Sanitization: The skill does not describe explicit sanitization or validation mechanisms for the project-provided verification instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 01:44 PM