jt-merge
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes git commands to verify development state, specifically using
git merge-base --is-ancestorto check if a branch has been merged andgit committo save changes to a tracking file. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes content from external files and git branch metadata which could theoretically contain malicious instructions.
- Ingestion points: The agent reads the content of
card-loop/board.mdand examines data (plans and diffs) from git branches identified bycard-<id>. - Boundary markers: The instructions lack explicit boundary markers or instructions to treat the ingested data as untrusted text.
- Capability inventory: The skill has permissions to write to the local file system (
card-loop/board.md) and execute shell commands through the git CLI. - Sanitization: No sanitization, filtering, or validation logic is specified for the data ingested from the board file or git branches before it is used to determine agent actions.
Audit Metadata