setup-skill-performance
Generate eval scenarios from a Tessl plugin (a packaged skill bundle), run baseline + with-context evals, and present results. Use when setting up an evaluation pipeline, running benchmarks, generating test scenarios, measuring skill performance or accuracy, scoring how well a skill helps agents solve tasks, or evaluating skill effectiveness before publishing.
89
92%
Does it follow best practices?
Impact
89%
1.14xAverage score across 29 eval scenarios
Low
Low-risk findings worth noting
The canonical home for this skill is tessl/skill-optimizer
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
The runtime workflow reads and evaluates outsider-authored free text embedded in the plugin evaluation artifacts (`task.md`, `criteria.json`, and related scenario files) that are generated/downloaded from the Tessl service and then ingested during `tessl eval run` (phases 2–4), where those files can contain arbitrary prompt-like instructions.
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 documents that a `commit`-type fixture like "https://github.com/acme/example.git" may be written into scenario.json (with user approval) and that the eval runner will git-clone that repo at eval runtime, creating a runtime external dependency that can bring remote code into execution (and be paired with setup.sh execution).
- Repository
- tesslio/product-plugins
- Commit
37f0a21
- 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.