write-release-notes
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and referenced guides do not contain any malicious patterns, obfuscation, or unauthorized access to sensitive files. It follows operational best practices by using temporary file paths for drafts.
- [COMMAND_EXECUTION]: The skill utilizes
gitandghcommands for repository interaction. These are well-defined, standard operations for the task and do not incorporate unvalidated user input directly into executable shell contexts beyond reading repository metadata. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as git logs and pull request descriptions. Although this represents a potential ingestion surface for indirect prompt injection, the risk is effectively mitigated by the skill's requirement for the user to review and explicitly approve the generated release notes before they are published to GitHub.
Audit Metadata