use-t3code-cli
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
t3codebinary to perform project resolution, handover threads, and environment diagnostics. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the
$HANDOVER_PROMPTenvironment variable or$handoverPromptPowerShell variable. - Ingestion points: The handover instructions in
SKILL.mdingest external content into the CLI via stdin. - Boundary markers: The skill does not define specific delimiters or instructions to the model to ignore embedded commands within the handover prompt.
- Capability inventory: The skill allows for local CLI execution and interaction with the T3 Code environment.
- Sanitization: No sanitization, validation, or filtering of the input prompt is specified.
- [EXTERNAL_DOWNLOADS]: The skill references an integration example at
github.com/MajesteitBart/delano. This is a vendor-owned resource associated with the skill author.
Audit Metadata