ideogram-observability
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input which is then transmitted to an external API, creating a surface for potential injection attacks.
- Ingestion points: The prompt argument in the instrumentedGenerate function located in SKILL.md.
- Boundary markers: No delimiters or boundary markers are used to isolate the prompt content from the request structure.
- Capability inventory: The skill performs network operations using fetch to https://api.ideogram.ai/generate.
- Sanitization: The skill lacks explicit sanitization or validation of the prompt string before processing it.
- [EXTERNAL_DOWNLOADS]: The skill references and utilizes the prom-client library for metrics collection.
- Evidence: Import statement and resource link to the official prom-client repository on GitHub.
Audit Metadata