CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/gitlab-api

Retrieve and analyze GitLab merge request comments and metadata using authenticated API calls

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

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 required runtime workflow fetches GitLab merge request comments via the `get_mr_comments.sh` script (publicly authored MR comment bodies by other users) and then passes that readable comment text into the agent for analysis, creating an indirect prompt-injection surface from outsider-authored free text.

Where we found it

gitlab.com

domain · 4 sites

The plugin's documented workflow fetches GitLab merge request comments (including outsider-authored comment bodies) via the get_mr_comments.sh script which calls the GitLab API at gitlab.com/api/v4/, then passes that comment text to the agent for analysis, creating an indirect prompt-injection surface.

SKILL.md

31

https://gitlab.[REDACTED]

SKILL.md

89

https://gitlab.com/group/project/-/merge_requests/ID

SKILL.md

115

https://gitlab.com/api/v3/projects/...

SKILL.md

116

https://gitlab.com/api/v4/projects/...

Report incorrect finding
Audited
Security analysis
Snyk