security-questionnaire-autofill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted content from third-party security questionnaires, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: Questionnaire content and posture documents are ingested into the agent context as described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the processed questionnaire data.
- Capability inventory: The skill contains no executable scripts and does not request access to any dangerous tools or system capabilities.
- Sanitization: No methods for validation or sanitization of input document content are defined.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, executables, or code files, which significantly reduces the risk of automated attacks.
Audit Metadata