umb-release-notes
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI (
gh) andjqto retrieve pull request details (titles, labels, authors) from theumbraco/Umbraco-CMSrepository. These operations are scoped to the official repository and are necessary for the skill's primary function. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of pull request titles and labels from GitHub and interpolates them into markdown files. While this creates a potential surface for indirect prompt injection if an attacker controls PR titles, the impact is confined to the content of the generated release notes file.
- Ingestion points: Pull request data fetched via
gh pr listandgh pr viewfrom GitHub, and the local input release notes file. - Boundary markers: None identified.
- Capability inventory: Shell command execution (
gh), local file reading, and local file writing. - Sanitization: None identified; the skill relies on the agent's internal processing logic for categorization.
Audit Metadata