commit-push-pr
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the dynamic context injection pattern in SKILL.md to execute shell commands at load time. Specifically, it runs
git status,git diff HEAD, andgit branch --show-currentto provide context to the agent. These are standard development workflow commands used to establish the current project state. - [INDIRECT_PROMPT_INJECTION]: The skill ingests potentially untrusted data from the local repository through the output of
git diff HEADandgit statuswithout sanitization or boundary markers. - Ingestion points: SKILL.md (via dynamic context commands
!git statusand!git diff HEAD). - Boundary markers: Absent. The output of the git commands is interpolated directly into the Context section without delimiters or instructions to ignore embedded commands.
- Capability inventory: The agent is instructed to create branches, perform commits, push to remote origins, and create pull requests using the
ghCLI tool. - Sanitization: Absent. There is no validation or filtering of the content returned by the git commands before it is processed by the agent.
Audit Metadata