tutorial
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The 'Prove the path' section explicitly instructs the agent to use the 'Bash' tool to run commands and verify the tutorial's output before returning it to the user. This involves executing shell commands in the agent's environment.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). Since the agent is instructed to execute code generated from user-supplied topics during its verification step, a malicious request could lead the agent to write and subsequently run harmful code.
- Ingestion points: The tutorial topic provided via the argument-hint '[topic or concept to teach]'.
- Boundary markers: None specified to differentiate user-controlled tutorial content from instructions.
- Capability inventory: The skill uses 'Bash', 'Write', 'Edit', and 'Read' tools to generate and verify code.
- Sanitization: No sanitization or validation of the user-provided topic or the resulting code is performed before execution.
Audit Metadata