principle-tagging
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a process where the agent consumes user-provided design references, establishing an attack surface for indirect prompt injection.
- Ingestion points: User-supplied design references as described in SKILL.md.
- Boundary markers: Absent; there are no defined delimiters or instructions for the agent to ignore potentially malicious embedded commands.
- Capability inventory: None; the skill consists only of instructional markdown without scripts, network access, or file-writing tools.
- Sanitization: Absent; no validation or filtering of input data is specified.
Audit Metadata