resource-tagging
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The
scripts/audit_tags.pyscript ingests resource tags and labels from cloud environments. These tags are external, user-controllable data. While the script is intended for governance auditing, the ingestion of untrusted data represents an attack surface for indirect prompt injection if the output is subsequently processed by an AI agent without strict data-to-instruction boundaries.\n - Ingestion points:
scripts/audit_tags.pyfetches tag keys and values from AWS, Azure, and GCP via cloud provider SDKs.\n - Boundary markers: The script outputs data in standard table or CSV formats without implementing specific delimiters or 'ignore instructions' markers to isolate external content.\n
- Capability inventory: The skill contains scripts for reading cloud metadata and infrastructure-as-code examples for resource management.\n
- Sanitization: Tag values are processed as raw strings without escaping sequences that could be interpreted as instructions in a prompt context.
Audit Metadata