The Agent Skills Directory

[SAFE]: The skill performs legitimate development tasks, such as reading git logs and creating local directories for documentation. All operations are local and align with the tool's stated purpose.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data from git commit messages which are then summarized by the agent.
Ingestion points: The outputs of git log and git diff commands are used as context for the retrospective.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potential instructions embedded within commit messages.
Capability inventory: The skill utilizes shell execution for git, date, and mkdir operations.
Sanitization: There is no evidence of sanitization or filtering of the commit data before it is processed by the agent.

rrr-lite