alterlab-cdm-film-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill is designed to assist with film studies through analysis, theory application, and essay drafting.
- [INDIRECT_PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection by design, as it ingests untrusted data from web searches and project files to perform research tasks.
- Ingestion points: Web search results and existing project files (SKILL.md, Agentic Protocol).
- Boundary markers: Absent; the instructions do not specify delimiters or warnings for processed data.
- Capability inventory: Web searching, reading files, and writing deliverables as Markdown files (SKILL.md, Capabilities).
- Sanitization: Absent; no explicit sanitization or validation of external content is defined.
Audit Metadata