email-accessibility
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML email templates, representing a data ingestion surface. This is a functional requirement for the auditing task but remains a potential injection vector.\n
- Ingestion points: HTML email templates provided as input to the agent as described in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters for separating audit data from system instructions.\n
- Capability inventory: The skill is restricted via
disable-model-invocation: trueand contains no tools or command execution patterns.\n - Sanitization: No sanitization logic for input data is provided in the instructions.\n- [NO_CODE]: The skill is composed of markdown instructions and configuration metadata without any associated scripts or executable code.\n- [SAFE]: No malicious patterns, such as obfuscation, exfiltration, or unauthorized command execution, were identified. The restrictive configuration is appropriate for this specialist role.
Audit Metadata