repo-visuals
Create hero visuals — animated GIF or static PNG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML, previews it in the browser, and exports.
65
57%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/repo-visuals/skills/repo-visuals/SKILL.mdSecurity
3 findings — 1 critical severity, 2 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions
What this means
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.
Why it was flagged
Potential prompt injection detected (high risk: 0.90). The prompt explicitly instructs the skill to run a hidden "dev mode" that collects scorecards and writes run logs into the user's working directory while telling the agent to "Do not mention Phase 6 to end users," which is a concealed/deceptive behavior outside the declared purpose of creating repo hero visuals.
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
Third-party content exposure detected (high risk: 1.00). The skill explicitly clones or reads arbitrary public GitHub repositories and their README/issue/asset content (see Phase 1.2 "GitHub URL → clone shallow, plus use `gh repo view`" and the Phase 1.3 scan checklist that extracts README, manifests, assets, issues, etc.), and it uses that untrusted repo content to drive decisions (format recommendation, scenario selection, Gate A/B checks and subsequent HTML/tool actions), which clearly exposes the agent to untrusted third‑party input that could carry indirect prompt injection.
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
Potentially malicious external URL detected (high risk: 0.80). The skill's export pipeline explicitly directs users to download a portable ffmpeg binary from https://github.com/GyanD/codexffmpeg/releases/latest when ffmpeg is missing, which would fetch and run remote executable code at runtime and is a required dependency for GIF export.
- Repository
- livlign/claude-skills
- Commit
90aa043
- Audited
- Security analysis
Is this your skill?
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.