personwise/personwise-sales-enablement-training
Reps repeat whatever the launch deck says — including the parts nobody approved. Turn your approved positioning and go-to-market materials into an interactive digital-human sales enablement training course that carries only cleared claims and answers rep questions on demand. Customer names, competitive advantages, and results are never invented.
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
In SKILL.md, the required runtime workflow has the agent classify a create request as `knowledge_source_mode=open` (“Create from a topic or supplied text”) and then uses PersonWise `course create --input <blueprint.json>`, meaning outsider-provided free text can be ingested/grounded as course knowledge without first selecting a specific trusted item.
Where we found it
user-supplied text (knowledge_source_mode=open)
content-type · 1 site
The scanner flags that knowledge_source_mode=open allows outsider-provided free text to be ingested as course knowledge. This corresponds to line 151 in SKILL.md which classifies 'Create from a topic or supplied text' as knowledge_source_mode=open.
SKILL.md
151
- **Create from a topic or supplied text:** `knowledge_source_mode=open`.
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 bootstrap scripts download and install the PersonWise CLI from remote release URLs at runtime (e.g., https://releases.personwise.ai/cli/v1.1.6/personwise_1.1.6_windows_amd64.zip and the template URL https://releases.personwise.ai/cli/v1.1.6/$artifact), meaning remote executable code is fetched and installed as part of the Skill's runtime.
Where we found it
PersonWise CLI 1.1.6 (releases.personwise.ai)
dependency · 1 site
The bootstrap.sh script downloads and installs the PersonWise CLI executable from remote release URLs at runtime (line 132), with platform-specific artifacts defined at lines 29, 40, 51, 62. This is remote executable code fetched and installed as part of the Skill's runtime.
assets/bootstrap.sh
132
url="https://releases.personwise.ai/cli/v1.1.6/$artifact"
- Audited
- Security analysis