release
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various shell commands to automate the release process.
- Evidence: It runs
mise run tagto trigger the release workflow and standardgitcommands (checkout,pull,tag,push) to manage repository state and tags. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted commit messages to generate release notes.
- Ingestion points: The release process (triggered in
SKILL.md) reads the project's Git commit history to generate a changelog using theclaudeCLI. - Boundary markers: Absent; there are no specific instructions or delimiters to ensure the agent ignores instructions potentially embedded within commit messages.
- Capability inventory: The skill has the ability to execute shell commands and write to files (
CHANGELOG.md,.release-notes.md). - Sanitization: No sanitization or filtering of Git logs is described before the content is passed to the LLM for summarization.
Audit Metadata