Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently connects an agent to Branddock so it can fetch brand context, draft content, score it, and leave approval to the user.
Install this if you intend to use Branddock for brand-aware drafting and scoring. Be aware that brand context and text you ask it to score or generate may be sent to Branddock, and approve paid generation actions deliberately, especially high-credit SEO, campaign, image, or video work.
The README’s instructional content is written in Dutch and does not indicate that language choice is optional or user-selectable. Under the policy rule for language or locale constraints, this can be a violation because it effectively imposes a specific language without opt-in or a stated region-specific justification.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# Full brand context
curl https://branddock.app/api/v1/brand-context \
-H "Authorization: Bearer bd_live_..."
# Score a text against the brand
The 'First prompts that work well' section provides only Dutch example prompts, which can create an implicit language preference in the skill's natural-language guidance. While the skill supports a brand's content language, these examples do not explicitly offer users a language choice or clarify that other languages are equally supported.