alphaxiv
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
2 findings: 1 critical severity, 1 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
The skill contains an explicit, mandatory instruction (Step 6) to always execute a local bash ingest script and forbids skipping it after delivering the summary, which is outside the advertised "quick single-paper reader" behavior and forces potential local command execution/exfiltration.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly mandates running a bash block that may execute a Python helper (python3 "$WIKI_SCRIPT" ingest_paper ...) which can modify the local repository (create/update pages, rebuild indexes, append logs) and thus changes the machine's filesystem and executes local code — so it pushes the agent to modify host state.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
Yes—at runtime the required workflow fetches outsider-authored free text from public web pages (AlphaXiv overviews/markdown via `curl` from `https://alphaxiv.org/...` and potentially arXiv LaTeX source from `https://arxiv.org/src/...`), which is then ingested into the agent’s LLM context as paper content.
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 explicitly fetches external Markdown and source archives at runtime and injects them into the model context to drive responses (https://alphaxiv.org/overview/{PAPER_ID}.md, https://alphaxiv.org/abs/{PAPER_ID}.md, https://arxiv.org/src/{PAPER_ID}).
- Commit
c5f3d5b
- 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.