The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses git revert and git log to manage project state. This capability is gated by mandatory confirmation prompts as defined in the skill's constraints.
[PROMPT_INJECTION]: There is a potential for indirect prompt injection via the processing of untrusted project data. 1. Ingestion points: The skill reads commit messages and plan file contents. 2. Boundary markers: No delimiters are specified to isolate external data. 3. Capability inventory: The skill can execute shell commands and modify files. 4. Sanitization: No sanitization of ingested content is performed, with the skill relying on user confirmation of the execution plan.

conductor-revert