recipe-front-plan
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection to execute a shell command (
! ls -la docs/design/*.md | head -10) when the skill is loaded. This command is used to display available design documents for user selection within the project directory and does not access sensitive system files or credentials. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from design documents.
- Ingestion points: Data enters the agent context from files located in
docs/design/*.md, which are then used to inform the prompts for sub-agents. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands when interpolating file paths or content into the prompts for
acceptance-test-generatororwork-planner. - Capability inventory: The skill has the ability to execute shell commands and invoke other specialized sub-agents to generate code and plans.
- Sanitization: No sanitization or validation of the content within the design documents is performed before it is passed to other components.
Audit Metadata