contest-page-generator
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill provides instructional content for promotional campaign design.\n- [INDIRECT_PROMPT_INJECTION]: The skill attempts to ingest project-specific goals from local files, which creates a potential surface for indirect prompt injection.\n
- Ingestion points: Reads campaign goals from
.claude/project-context.mdand.cursor/project-context.mdas specified in SKILL.md.\n - Boundary markers: None identified; instructions do not specify delimiters for external data.\n
- Capability inventory: Limited to text generation; no subprocess calls, network operations, or file-write actions were found across the skill.\n
- Sanitization: None identified for the ingested content.
Audit Metadata