create-verification-skill
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the automated creation and execution of verification logic based on untrusted repository content. \n
- Ingestion points: The agent is directed to read and interpret project-local artifacts such as package scripts, Makefiles, documentation, and source code to determine how to drive the application (SKILL.md, Section 1). \n
- Boundary markers: There are no instructions provided to use specific delimiters or protective wrappers when processing this external data during the interview phase. \n
- Capability inventory: The workflow requires the agent to execute shell commands to build the project, launch the application, and run test harnesses to validate the generated skill (SKILL.md, Section 4). \n
- Sanitization: The skill does not include instructions for validating or sanitizing the commands or parameters extracted from the repository before they are executed by the agent.
Audit Metadata