adobe-observability
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by processing external data and possessing file-modification capabilities.
- Ingestion points: The skill uses Read, Glob, and Grep tools to inspect documentation, configuration, and fixtures as specified in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or instructions to the agent to isolate untrusted external content from its own execution logic.
- Capability inventory: The skill is authorized to use Write and Edit tools to create or modify repository artifacts.
- Sanitization: The skill contains robust instructions for redacting secrets, PII, and sensitive content, and includes error handling to stop exports if canaries are detected.
- [SAFE]: The skill references official developer documentation from Adobe, which is recognized as a well-known and trusted service.
Audit Metadata