iblai-api-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides examples for downloading the OpenAPI schema and fetching analytics data from api.iblai.app. These operations target the official vendor infrastructure and are used for service validation and intended data retrieval.
- [INDIRECT_PROMPT_INJECTION]: The skill serves as a surface for indirect prompt injection because it ingests external data, specifically chat transcripts and user-generated content, into the agent context.
- Ingestion points: Transcript and message detail endpoints in SKILL.md.
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions within the ingested transcript data.
- Capability inventory: The skill uses curl for network requests and interacts with the local file system (e.g., writing to /tmp/iblai_schema.yaml).
- Sanitization: No specific sanitization or filtering logic is described for the content returned by the analytics API.
Audit Metadata