jt-send-back
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local project files to determine execution logic, such as branch names and card identifiers.
- Ingestion points: Data is read from
card-loop/board.mdandcard-loop/plan/<id>.mdas described inSKILL.md. - Boundary markers: The instructions do not define explicit markers or isolation for the data read from these files.
- Capability inventory: The skill performs file system modifications and executes git commands (checkout, commit) as described in
SKILL.md. - Sanitization: No sanitization or validation of the data extracted from project files is specified.
- [COMMAND_EXECUTION]: The skill requires the agent to execute git commands to manage project branches and commits.
- Evidence: Instructions in
SKILL.mdspecify checking out branches based on file content and committing specific markdown files.
Audit Metadata