skills/pluginagentmarketplace/custom-plugin-mongodb/mongodb-indexing-optimization/Gen Agent Trust Hub
mongodb-indexing-optimization
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected in the skill's data processing logic.
- Ingestion points: The
SKILL.mdfile defines input validation requirements forquery_patternandcollection_info, which are points where untrusted data enters the agent's context. - Boundary markers: No explicit delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings are used to wrap the input variables.
- Capability inventory: The skill includes high-impact capabilities such as
index-design,explain-analysis, andquery-optimizationwhich generate and interpret database-specific logic based on the inputs. - Sanitization: The provided files lack explicit sanitization or validation rules to ensure that the input query patterns do not contain malicious instructions intended to manipulate the agent's recommendations.
Audit Metadata