services-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill suggests reading local context files which could potentially contain untrusted instructions if a project is compromised.
- Ingestion points: .claude/project-context.md and .cursor/project-context.md (in SKILL.md).
- Boundary markers: Absent; instructions do not include delimiters for the external context.
- Capability inventory: None; the skill does not use tools or execute scripts.
- Sanitization: Absent.
- [SAFE]: The skill is composed of static documentation and instructional text. It does not perform network requests, file system writes, or command execution.
Audit Metadata