ansoff-matrix
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-provided data via the
$ARGUMENTSvariable directly into the instructions. - Ingestion points:
SKILL.mduses$ARGUMENTSto define the context for the growth strategist persona. - Boundary markers: The instructions lack explicit delimiters (like XML tags or triple quotes) or negative constraints to prevent the agent from following instructions embedded within the user-supplied arguments.
- Capability inventory: The skill relies on the agent's core generative and reasoning capabilities; no external tools or file system operations are explicitly requested in the instructions.
- Sanitization: There is no evidence of input validation or sanitization before the
$ARGUMENTSare processed by the model.
Audit Metadata