CtrlK
BlogDocsLog inGet started
Tessl Logo

personwise/personwise-sales-onboarding

New sales reps ramp on whatever they find — including claims nobody approved. Turn your sales playbook into an interactive digital-human sales onboarding course that ramps new reps on approved stories, process, and proof, and answers their questions before the first call. Scoped to the new sales rep ramp; broader readiness belongs to sales enablement.

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Low

Low-risk findings.

2 low severity findings. Worth noting, but not necessarily harmful.

Low

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’s runtime workflow, the agent can ingest learner-supplied “supplied text” when it classifies creation as `knowledge_source_mode=open` (i.e., not just strictly user-selected documents), which permits outsider-authored free text to be used as LLM input.

Where we found it

learner-supplied free text (knowledge_source_mode=open)

content-type · 1 site

The skill explicitly allows `knowledge_source_mode=open` which accepts "supplied text" from the learner, meaning outsider-authored free text can be ingested as LLM input.

SKILL.md

151

- **Create from a topic or supplied text:** `knowledge_source_mode=open`.

Report incorrect finding
Low

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 installers download and install a remote CLI executable at runtime (e.g., "https://releases.personwise.ai/cli/v1.1.6/personwise_1.1.6_windows_amd64.zip" and "https://releases.personwise.ai/cli/v1.1.6/$artifact"), which fetches and installs remote code the Skill requires to run.

Where we found it

PersonWise CLI v1.1.6 (downloaded from releases.personwise.ai)

dependency · 4 sites

The skill's bundled bootstrap installer (bootstrap.sh) downloads and installs a remote CLI executable from releases.personwise.ai at runtime, fetching and installing remote code the skill requires to run.

assets/bootstrap.sh

132

url="https://releases.personwise.ai/cli/v1.1.6/$artifact"

SKILL.md

78

run the bundled `assets/bootstrap.sh --approve-install` on Linux/macOS

79

or `assets/bootstrap.ps1 --approve-install` on Windows

130

`assets/bootstrap.sh --approve-upgrade` on Linux/macOS, `assets/bootstrap.ps1 --approve-upgrade` on Windows

Audited
Security analysis
Snyk