Create a Trellis migration manifest and matching docs-site changelogs for a target release by analyzing commits since the previous release. Use when preparing a patch, beta, rc, or minor release manifest.
77
96%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
This workflow’s runtime text ingestion is from `git log` output over commit history (i.e., commit messages/diffs authored by other contributors), and that content is then used to generate release notes/changelog via the agent/LLM—so outsider-authored free text can enter the LLM context indirectly via VCS commit metadata/diffs.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill includes the runtime command "npx -y @mindfoldhq/trellis@<last-ga>" which fetches and executes remote npm package code (and the file also references the npm registry URL https://registry.npmjs.org/), so remote code is executed at runtime.
12e279a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.