The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from external, potentially untrusted sources including GitHub PR comments and detailed HTML reports.
Ingestion points: The workflow in SKILL.md requires the agent to parse GitHub comments and external report URLs to identify code behavior changes.
Boundary markers: The skill does not define clear delimiters or instructions to ignore embedded commands within the external content being analyzed.
Capability inventory: The agent has the ability to execute shell commands (uvx prek), load additional skills (minimizing-ty-ecosystem-changes), and coordinate sub-agents.
Sanitization: There are no explicit steps to sanitize or filter the external text before it is processed by the agent or sub-agents.
[COMMAND_EXECUTION]: The skill executes the prek tool via uvx on the final generated summary file. While uvx and prek are tools associated with the skill author (Astral), executing packages directly from a registry without version pinning is a noted capability.

summarise-ecosystem-results