asd-ste100
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a natural surface for indirect prompt injection as it is designed to ingest and transform arbitrary technical text.
- Ingestion points: External copy, procedural steps, and agent outputs passed to the skill for rewriting according to ASD-STE100 rules in
SKILL.md. - Boundary markers: No explicit delimiters are defined in the instructions to separate untrusted input from the transformation logic.
- Capability inventory: The skill contains no executable code, command execution patterns, file system access, or network communication capabilities.
- Sanitization: Input text is processed based on linguistic rules without explicit sanitization or filtering of the content.
Audit Metadata