ascii-motd-profile-banner
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-supplied strings for banner titles and message bullets without performing sanitization, which could allow malicious instructions to be embedded in the output banners.
- Ingestion points: The
titleandmessageBulletsparameters defined inSKILL.md. - Boundary markers: Absent; there are no clear delimiters or instructions provided to the agent to isolate user-supplied data from executable instructions.
- Capability inventory: While the skill itself is restricted to generating text templates, the agent's execution environment typically possesses file system and shell capabilities that could be targeted.
- Sanitization: No validation, escaping, or filtering of the input content is performed.
Audit Metadata