release
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute various development and release commands including
git(for tagging and pushing),gh(GitHub CLI for release management and workflow monitoring), andnpm/pnpm(for building, testing, and publishing packages). - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data and interpolating it into prompts or using it to drive subsequent actions.
- Ingestion points: Reads project configuration files (
package.json,Cargo.toml,Cargo.lock,tauri.conf.json), local git command outputs (git tag,git log), and remote API outputs from GitHub (gh run view,gh release view) and npm (npm view). - Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore potentially malicious content embedded in these external sources.
- Capability inventory: The agent has the capability to execute shell commands (
Bash), write files (pnpm build), and perform network operations via CLI tools (npm publish,gh api). - Sanitization: There are no explicit sanitization steps defined for the data ingested from git logs or GitHub API responses before they are used to generate release notes or influence the workflow.
Audit Metadata