oh-my-ai/humaniser
Removes common AI-writing tells and rewrites prose to sound natural and human, using an interactive intake, voice calibration, and a second-pass audit.
97
97%
Does it follow best practices?
Impact
100%
1.00xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The SKILL.md explicitly states it uses "WebSearch/WebFetch when the user wants terminology or usage research," meaning the agent will fetch and read open/public third‑party web content as part of its workflow, which could materially influence rewriting decisions and enable indirect prompt injection.
- Audited
- Security analysis