The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as GitHub Pull Requests, issues, and logs, which presents a surface for indirect injection attacks.
Ingestion points: External data enters the agent's context through commands in SKILL.md such as gh pr view, gh run view, and npx ruv-swarm actions detect-changes.
Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potentially malicious content embedded within the ingested data.
Capability inventory: The skill has the capability to write to the local filesystem (generating .github/workflows/ files), execute shell commands via npx, and perform network operations via the GitHub CLI (gh).
Sanitization: There is no evidence of sanitization or validation performed on the external content before it is processed by the AI swarm agents.
[COMMAND_EXECUTION]: The skill makes extensive use of shell command execution to perform its primary tasks, including generating workflows, analyzing failures, and managing repository states.
[EXTERNAL_DOWNLOADS]: The skill downloads and executes vendor-provided tools (ruv-swarm, claude-flow@alpha) from the npm registry at runtime using npx.

github-workflow-automation