changelog-polish
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses local repository files including
STYLE.md,products.yml, andREADME.md. This access is necessary for the skill to perform its primary function of validating changelog entries against established project guidelines. - [COMMAND_EXECUTION]: The skill includes an instruction to use a 'Write' tool to update files with the polished content, but only after receiving explicit user confirmation.
- [PROMPT_INJECTION]: The skill evaluates untrusted user-provided text in the form of changelog drafts. This creates a surface for indirect prompt injection; however, the skill proactively instructs the agent to detect and remove dangerous patterns such as raw HTML,
<script>, and<iframe>tags from the draft content.
Audit Metadata