writing-content
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected. The skill's functionality is limited to text generation, style comparison, and self-checks for content quality.
- [COMMAND_EXECUTION]: The skill includes instructions to invoke
/spencergo:writing-reviewvia a tool call. This is a legitimate workflow transition to another module within the same developer's suite (spencerkit) and does not constitute arbitrary or dangerous command execution. - [EXTERNAL_DOWNLOADS]: The README mentions installation via a marketplace command pointing to the author's own repository (
spencerkit/spencergo-marketplace). This is standard installation behavior for the platform and does not involve untrusted third-party sources. - [PROMPT_INJECTION]: The instructions contain a 'MUST FOLLOW' directive for the workflow phase. This is used for state management and ensuring the agent transitions to the review phase, rather than attempting to bypass safety filters or override system constraints.
Audit Metadata