manim-composer
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it is instructed to perform deep research on topics using web search and then incorporate those insights into its output.\n
- Ingestion points: Web search results for core concepts and aha moments as defined in Phase 1 (SKILL.md).\n
- Boundary markers: The skill does not provide specific instructions or delimiters to isolate or ignore potentially malicious instructions embedded in search results.\n
- Capability inventory: The skill uses web search and produces a scenes.md file; it lacks high-privilege capabilities such as arbitrary shell command execution or environment variable access.\n
- Sanitization: No mechanisms for sanitizing or validating the content retrieved from external sources are present in the instructions.
Audit Metadata