implement
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes external documentation such as PRDs or issues which may contain adversarial instructions designed to influence the agent's behavior during the implementation phase.
- Ingestion points: Processes external PRDs and issue sets (SKILL.md).
- Boundary markers: Absent. There are no instructions or delimiters used to separate user data from system instructions.
- Capability inventory: The skill has the capability to write code, execute local shell commands (typecheckers and test runners), and perform git operations (SKILL.md).
- Sanitization: Absent. The skill does not perform validation or filtering on the content of the PRDs or issues before acting upon them.
- [COMMAND_EXECUTION]: Local Command Execution. The skill instructs the agent to run typecheckers and test suites. While this is standard for a development tool, these commands operate on the code generated from potentially untrusted inputs, creating a risk if the generated code contains malicious hooks.
Audit Metadata