solutions-page-generator
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by directing the agent to read and process data from external project context files.
- Ingestion points: The skill instructs the agent to read
.claude/project-context.mdor.cursor/project-context.mdinSKILL.mdto identify project context. - Boundary markers: There are no instructions provided to use delimiters or specific boundary markers when interpolating this external content into the prompt.
- Capability inventory: The skill does not possess any dangerous capabilities such as file-write operations, network requests, or subprocess execution; its function is limited to text generation.
- Sanitization: There is no mention of sanitizing or validating the content retrieved from the project context files before it is processed by the agent.
Audit Metadata