The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill is vulnerable to indirect prompt injection because it incorporates untrusted data from the local environment into the agent's decision-making process. ● Ingestion points: The command git diff HEAD reads the contents of all changed files, which could include malicious instructions planted by an attacker. ● Boundary markers: There are no boundary markers, delimiters, or system-level instructions provided to the agent to treat the diff output as data rather than instructions. ● Capability inventory: The skill explicitly allows the agent to execute git add -A and git commit, which are write operations that can be used to persist malicious changes or execute further commands if the agent is manipulated. ● Sanitization: No sanitization, filtering, or validation is performed on the output of the git commands before the agent processes them.
[Command Execution] (LOW): The skill's core functionality relies on executing shell commands (git). While necessary for the stated purpose, this provides the agent with a direct interface to the underlying filesystem, which increases the impact of a successful prompt injection attack.

commit