Specialized release management for morphir-dotnet. Use when user asks to prepare releases, execute releases, monitor deployments, validate releases, resume failed releases, update changelog, create release notes, or manage release workflow. Triggers include "release", "deploy", "publish", "changelog", "version", "release notes", "what's new".
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/release-manager/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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.
Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and parses public, user-generated content (GitHub PRs, issues, and Actions workflow logs via the gh CLI in monitor-pr.fsx, monitor-release.fsx, resume-release.fsx and prepare-release.fsx) and queries NuGet.org (validate-release.fsx), and those parsed results directly drive decisions like auto-merge, resume/retrigger workflows, and release actions—so untrusted third-party content can materially influence tool use.
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.
Potentially malicious external URL detected (high risk: 0.70). The F# scripts include runtime package directives that fetch and execute remote NuGet packages (e.g. #r "nuget: Argu, 6.2.4" and #r "nuget: Spectre.Console, 0.53.0"), which causes code to be downloaded from NuGet.org at script runtime and thus are external runtime dependencies that execute remote code.
7c0c06d
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.