poster-design
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from a local file which could potentially contain malicious instructions if the file is compromised.
- Ingestion points: The skill reads branding and style context from
.agents/design-context.md(specified in Step 1 of SKILL.md). - Boundary markers: None. The skill does not provide delimiters or instructions to ignore potential commands embedded within the design context file.
- Capability inventory: The skill generates complex HTML, CSS, and SVG code which is then rendered or executed in the user's environment.
- Sanitization: There is no evidence of validation or sanitization for the content loaded from the configuration file.
Audit Metadata