contest-page-generator

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation providing templates, best practices, and structure for promotional campaigns. No executable scripts, binaries, or active code components are present in the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions include a step to read project context files (.claude/project-context.md or .cursor/project-context.md) to align with project goals.
  • Ingestion points: Files located at .claude/project-context.md and .cursor/project-context.md (specified in SKILL.md).
  • Boundary markers: None explicitly defined for the ingestion of these files.
  • Capability inventory: No scripts or executable capabilities are provided within this skill; it only provides text generation guidance.
  • Sanitization: None specified.
  • Assessment: While reading local files represents an ingestion surface for indirect prompt injection, the lack of any dangerous capabilities (network, file-write, or command execution) within the skill itself renders this risk negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:08 PM
Security Audit — agent-trust-hub — contest-page-generator