Turn any markdown file into a publication-quality PDF. (gstack)
Security
2 findings: 2 critical severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The SKILL.md embeds many operational instructions (telemetry logging and opt-in flows, automatic edits/commits to CLAUDE.md, artifact-sync/publish prompts, and background brain/telemetry commands) that direct the agent to take actions outside the stated "make-pdf" purpose and thus constitute hidden/deceptive side-effect instructions.
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
The list includes a GitHub repo (oschwartz10612/poppler-windows) that points to a personal GitHub distribution of Poppler for Windows — a user-maintained release page used to distribute binaries (high-risk per the rules: unknown GitHub username / personal executable distribution).
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.
In the make-pdf skill’s runtime path, the agent reads the user-selected markdown file content at `src/orchestrator.ts` (Stage 1: `fs.readFileSync(input, "utf8")`) and then feeds that resulting HTML into the Chromium renderer via `browseClient.loadHtml({ html: finalHtml, ... })`, so outsider-authored free text can be ingested.
d078622
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.