docs-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read external project files which serves as a potential attack surface for untrusted data ingestion.
- Ingestion points: The skill reads
.claude/project-context.mdand.cursor/project-context.mdto determine project details such as audience and product type. - Boundary markers: None; there are no instructions to the agent to treat the content of these files as untrusted or to ignore embedded instructions.
- Capability inventory: No dangerous capabilities are present; the skill only generates text-based documentation outlines and does not invoke network, file-write, or shell execution tools.
- Sanitization: None; the data from the context files is used directly to inform the generated documentation structure.
- [SAFE]: The skill's primary purpose is providing structural guidance for documentation. All instructions are benign, and there are no signs of malicious patterns such as remote code execution, persistence, or data exfiltration.
Audit Metadata