testmuai/kane-cli
Kane CLI by TestMu AI (Formerly LambdaTest). Use kane-cli for end-to-end browser and mobile testing in natural language: generate tests from a PRD or spec, run them on Chrome, Android and iOS, and gate CI with evidence packs.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 consumes outsider-authored free text through Jira issue URLs, Confluence page URLs, Linear issue/document URLs, and web page URLs ingested via `kane-cli context ingest`. External users can author the content of these pages and tickets, which are subsequently processed by the agent skill's required assurance ingestion workflow.
Where we found it
linear.app
domain · 4 sites
The skill ingests Linear issue and document URLs via `kane-cli context ingest`, fetching content from linear.app (a fixed external host) that outsider users can author, which is then processed by the agent's assurance workflow.
references/assurance.md
79
kane-cli context ingest https://linear.app/<workspace>/issue/KEY-123
80
Linear document URLs (0.8.6+) — …/document/<slug>
233
Linear issues and documents (0.8.6+)
references/agent-contract.md
79
provider (web, jira, confluence, linear, linear-doc)
Jira issue URLs (user's Jira instance)
content-type · 4 sites
The skill ingests Jira issue URLs via `kane-cli context ingest`, fetching issue content (including comments) from the user's Jira instance — an external source that outsider users can author, processed by the agent's assurance workflow.
references/assurance.md
77
Jira issue URLs (0.6.11+) — kane-cli context ingest https://<site>/browse/PROJ-123
233
Jira/Confluence (0.7.2+)
references/agent-contract.md
79
provider (web, jira, confluence, linear, linear-doc)
268
NO_ISSUE_ACCESS, NO_CONFLUENCE_ACCESS
Confluence page URLs (user's Confluence instance)
content-type · 4 sites
The skill ingests Confluence page URLs via `kane-cli context ingest`, fetching page content from the user's Confluence instance — an external source that outsider users can author, processed by the agent's assurance workflow.
references/assurance.md
78
Confluence page URLs (0.7.2+) — kane-cli context ingest https://<site>/wiki/spaces/<KEY>/pages/<id>/…
233
Jira/Confluence (0.7.2+)
references/agent-contract.md
79
provider (web, jira, confluence, linear, linear-doc)
268
NO_ISSUE_ACCESS, NO_CONFLUENCE_ACCESS
Web page URLs (any public http(s) URL)
content-type · 4 sites
The skill ingests arbitrary web page URLs via `kane-cli context ingest`, fetching content from any public http(s) URL (excluding Jira/Confluence/Linear) — external sources that outsider users can author, processed by the agent's assurance workflow.
references/assurance.md
81
Web page URLs (0.8.3+) — any public http(s) URL that is not a Jira/Confluence/Linear URL; fetched server-side
33
URL sources are fetched server-side, and a web page's ingest is refused when the organisation is out of credits
233
web pages (0.8.3+)
references/agent-contract.md
79
provider (web, jira, confluence, linear, linear-doc)
- Audited
- Security analysis