promo-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within a restricted file system scope, accessing only promotional markdown files and local rule definitions within the artist's project directory structure.\n- [SAFE]: A human-in-the-loop mechanism is enforced for all content revisions, ensuring that the agent does not autonomously modify files without user review and confirmation.\n- [SAFE]: The skill uses a restricted set of tools (Read, Edit, Glob, Grep) and does not perform any network operations, external downloads, or execution of arbitrary code.\n- [SAFE]: While the skill ingests external data from markdown files which represents a potential surface for indirect prompt injection, the strictly defined workflow and mandatory user approval step effectively mitigate this risk.
Audit Metadata