paker-it/aie26-skill-judge
Evaluates SKILL.md submissions for the AI Engineer London 2026 Skills Contest across 11 dimensions (8 official Tessl rubric + 3 bonus). Use when you say 'judge my AIE26 contest skill', 'score this SKILL.md for the contest', 'review my skill submission', or 'how would this score on the leaderboard'. Accepts GitHub repo URLs, file paths, or raw pastes.
82
94%
Does it follow best practices?
Impact
65%
1.80xAverage score across 5 eval scenarios
Risky
Do not use without reviewing
Security
3 findings — 1 high severity, 2 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 1.00). The prompt requires the agent to quote verbatim evidence from user-provided SKILL.md (including raw pastes or files), so if those files contain API keys, tokens, or passwords the agent will echo them in its output, creating an exfiltration risk.
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: 0.90). The SKILL.md Input Handling and Design sections explicitly state the skill accepts GitHub repo URLs and will "fetch the SKILL.md from the repo root using `gh` CLI or web fetch", meaning the agent will ingest arbitrary public, user-generated repository content and then read/interpret it to drive scoring and actions — creating a clear avenue for 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: 1.00). The SKILL.md explicitly accepts and at runtime fetches GitHub repository URLs (e.g., https://github.com/...) using the gh CLI or web fetch to load a remote SKILL.md which is then injected into the agent's context and directly controls prompts/instructions, so this is a runtime external dependency that can control the agent.
- Audited
- Security analysis