system-audit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on the ingestion of external and potentially untrusted data during the audit process, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The 'Gather Information' section in SKILL.md directs the agent to read architecture documentation, design documents, code structure, infrastructure-as-code, and deployment pipelines.
- Boundary markers: The instructions do not specify the use of delimiters or protective prompt wrappers to prevent the agent from following instructions that might be embedded in the materials being audited.
- Capability inventory: The skill file itself consists entirely of markdown instructions and does not include any scripts, subprocess calls, or network operations, though the agent may use its native tools to perform the requested reads.
- Sanitization: The skill lacks instructions for validating or sanitizing the content retrieved from external documents or codebases before processing.
Audit Metadata