changelog
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
node:child_processmodule to executegit,node,gh(GitHub CLI), andpnpmcommands. These are used to analyze repository state, fetch pull request metadata, and perform version stamping. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the repository's environment to populate changelog fields.
- Ingestion points: Commit messages (
git log), branch names, and pull request data retrieved from the GitHub API. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands when interpolating external content into the changelog markdown.
- Capability inventory: The agent can execute shell commands and perform filesystem write operations.
- Sanitization: While the scripts use regular expressions to extract specific patterns like issue IDs and conventional commit categories, they do not comprehensively sanitize the prose descriptions derived from commits or branch names.
Audit Metadata