jt-new-card
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files (
card-loop/brief.md,card-loop/board.md) and user input to determine the content of new cards and the state of the project board. - Ingestion points: The skill explicitly reads
card-loop/brief.md,card-loop/board.md, and interacts with user-provided responses during the interview phase (SKILL.md). - Boundary markers: None detected. The instructions do not specify delimiters or provide warnings to the agent to disregard instructions that might be embedded within the
brief.mdfile. - Capability inventory: The skill performs file system writes (creating
.mdfiles incard-loop/backlog/and modifyingcard-loop/board.md) and executes Git commands (git checkout,git commit) to persist changes. - Sanitization: No sanitization, escaping, or validation of the content read from the project brief or user input is described before it is processed by the agent.
Audit Metadata