evaluate
Evaluate execution with three-stage verification pipeline
53
60%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude-plugin/skills/evaluate/SKILL.mdThe canonical home for this skill is evaluate in Q00/ouroboros
Low
Low-risk findings.
1 low severity finding. 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 skill loads and runs an MCP evaluation tool (`ouroboros_start_evaluate`) using a `session_id` and an `artifact` that can include user-specified file contents and recent execution outputs, so outsider-authored free text can be ingested at runtime via the user/queue-provided artifact/session context.
- Repository
- Q00/ouroboros
- Commit
80333ae
- 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.