The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests data from external repository files which could be manipulated by third parties via pull requests.
Ingestion points: The skill reads from .maestro/ configuration files, reviews/summary.md, and test markers (last-verify.json) using the Read and Grep tools.
Boundary markers: There are no explicit delimiters or boundary markers specified in the instructions to isolate the ingested file content from the agent's core instructions.
Capability inventory: The skill is authorized to use the Bash and Write tools to aggregate findings and save the final report to the repository.
Sanitization: No specific sanitization or validation routines are defined for the data extracted from these files before they are processed by the agent.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform repository data aggregation tasks, such as generating diff summaries and checking for file markers, which is consistent with its stated purpose of assembling evidence-backed review packs.

human-review-pack