The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process rule files from the .agent-team/rules/ directory. This creates a vulnerability surface where instructions embedded within those files could influence agent behavior.
Ingestion points: Reads .agent-team/rules/index.md and specific rule files implicated by sync requests as stated in SKILL.md.
Boundary markers: Absent; there are no instructions or delimiters defined to prevent the agent from following prompts found within the ingested files.
Capability inventory: The skill is authorized to execute the agent-team rules sync CLI command.
Sanitization: Absent; the skill does not perform validation or filtering of the content within the rule files before processing.
[COMMAND_EXECUTION]: The skill is configured with a CLI binding to execute the agent-team rules sync command on the local system.

rules-maintenance