The Agent Skills Directory

[PROMPT_INJECTION]: Potential for indirect prompt injection via processed git history.
Ingestion points: Data enters the context through git log and git diff command outputs in SKILL.md.
Boundary markers: The skill does not use specific delimiters or instructions to the agent to isolate the untrusted git output from the task instructions.
Capability inventory: The skill has access to the Bash tool for running git log, git diff, and git rev-parse.
Sanitization: No filtering or validation is performed on the commit messages or code diffs before they are processed by the agent.

diff-summary