build-alone
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requirements and tickets which may contain untrusted data, and it possesses significant capabilities to influence the environment.
- Ingestion points: The agent ingests natural language requirements, feature requests, and ticket descriptions to drive the implementation process.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the skill's instructions and the content of the requirements, nor are there warnings to ignore embedded instructions.
- Capability inventory: The skill is authorized to create git branches (
/work-in-branch), modify the codebase, and execute shell commands for testing and linting (/full-verification). - Sanitization: No sanitization or validation mechanisms are defined for the input requirements before they are acted upon.
- [COMMAND_EXECUTION]: The skill leverages other tools to discover and run test and lint commands (
/find-verification-tools). This allows the agent to execute shell commands determined by the content of the repository it is working on, which could be exploited if the repository contains malicious configuration files.
Audit Metadata