context-degradation
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
70
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
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: 0.70). The skill’s runtime workflow ingests the agent’s current `context`/`context string` (e.g., passed into `ContextHealthAnalyzer.analyze(context, ...)` and `PoisoningDetector.detect_poisoning(context)`), and that context commonly includes outsider-authored free text such as prior user messages or retrieved web/document content; the skill itself does not filter provenance before feeding it into the LLM.
- Commit
c578e85
- 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.