personwise/personwise-customer-education
Customers keep asking the same questions, and every repeat answer costs support time. Turn your help content and product knowledge into an interactive digital-human customer education course that answers learner questions on its own — a customer academy asset for your help center, portal, or CSM follow-ups. Account-specific diagnosis always routes back to your support team.
66
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. 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 runtime workflow builds a course grounded in “the user’s own help center articles, product documentation, or support playbooks” and only accepts user-supplied materials via `personwise ... source add --path <exact-path>`, meaning outsider-authored free text can be ingested if the user selects or provides it.
Where we found it
user-supplied files via source add --path
content-type · 1 site
The scanner claims third-party content exposure via source add --path, but the plugin only processes user-supplied files explicitly provided by the user; it does not fetch any external content at runtime.
SKILL.md
205
personwise --account <alias> source add --run-id <run-id> --path <exact-path> --json
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The Skill's bundled bootstrap scripts fetch and install a remote executable at runtime from https://releases.personwise.ai/cli/v1.1.6/$artifact (and specifically https://releases.personwise.ai/cli/v1.1.6/personwise_1.1.6_windows_amd64.zip), which downloads and installs code the Skill relies on to operate.
Where we found it
releases.personwise.ai
domain · 2 sites
The bootstrap.sh script fetches and executes the PersonWise CLI v1.1.6 from releases.personwise.ai at runtime using curl, making it an unverifiable external dependency.
assets/bootstrap.sh
132
url="https://releases.personwise.ai/cli/v1.1.6/$artifact"
assets/bootstrap.sh
134
curl --disable --fail --silent --show-error --proto '=https' --tlsv1.2 --connect-timeout 10 --max-time 300 --max-filesize "26214400" --output "$archive" "$url"
- Audited
- Security analysis