tek-do-card
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands specified in the
card-loop/board.mdfile. Specifically, it retrieves and runs placeholders like<TEST_CMD>,<TYPECHECK_CMD>, and<LINT_CMD>during the action phase. - [INDIRECT_PROMPT_INJECTION]: The skill's behavior and logic are driven by the content of external files, creating a surface for injection.
- Ingestion points: The agent reads task instructions and execution parameters from
card-loop/board.mdand individual card files incard-loop/backlog/. - Boundary markers: No specific delimiters or safety instructions are used to separate the skill's core logic from the data ingested from these files.
- Capability inventory: The skill can execute arbitrary shell commands (via the board configuration), perform Git operations (checkout, branch, commit, push, merge request), and modify the local file system.
- Sanitization: There is no evidence of validation or sanitization of the commands or instructions retrieved from the local markdown files before they are executed or followed.
- [DYNAMIC_EXECUTION]: The skill dynamically assembles and executes shell commands at runtime based on variables retrieved from the project's board configuration.
Audit Metadata