The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute shell commands, specifically leveraging the GitHub CLI (gh), git, and npm for release management. It also provides examples for running builds inside Docker containers for isolation.
[EXTERNAL_DOWNLOADS]: The skill uses npx to execute vendor-related tools including claude-flow and ruv-swarm for release orchestration and swarm initialization.
[INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection because it ingests external data that is not fully controlled by the skill author.
Ingestion points: The skill fetches commit messages and Pull Request titles, labels, and bodies from the GitHub API (SKILL.md and references/workflows.md) to generate changelogs and version suggestions.
Boundary markers: No explicit delimiters or instructions are provided to the agent to prevent it from following instructions that might be maliciously embedded in commit messages or PR descriptions.
Capability inventory: The skill possesses high-privilege capabilities, including arbitrary command execution (Bash), file system writes (Write), and the ability to publish packages to external registries (npm publish, docker push).
Sanitization: There is no evidence of sanitization or filtering of the ingested commit and PR data before it is used to influence the agent's release preparation tasks.

github-release-management