ai-eval-playbook
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches live documentation from
eval.playbook.org.aito ensure use of the most current framework version and references a repository hosted by the IDinsight organization on GitHub. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes data from an external website to generate responses.
- Ingestion points: Data is retrieved from the
eval.playbook.org.aidomain using web fetching and indexing tools. - Boundary markers: The instructions lack specific delimiters or directive warnings to ignore potential malicious instructions embedded within the fetched external content.
- Capability inventory: The agent possesses the ability to read local workspace files (
mel_wiki/wiki/frameworks/) and utilize network tools for information retrieval. - Sanitization: There is no evidence of content sanitization or verification performed on the retrieved remote data before it is processed by the agent.
Audit Metadata