dogfood
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to identify and execute a shell command for running the application locally, which is sourced from the
docs/agents/project.mdfile. This pattern introduces a risk of command injection if the documentation file is maliciously modified. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from various project files (
requirements.md,design.md,tasks.md) to generate an interactive HTML artifact without implementing boundary markers or sanitization. - Ingestion points: Project documentation files and application source code.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the ingestion flow.
- Capability inventory: The skill utilizes file system read/write access and shell command execution.
- Sanitization: There is no evidence of escaping or validating external content before it is interpolated into the HTML output.
Audit Metadata