mindmap
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text or image content to create a Markdown file, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads user-provided text or image content to perform its primary function (SKILL.md).
- Boundary markers: The instructions do not include specific delimiters or warnings to ensure the agent ignores instructions embedded within the input source.
- Capability inventory: The skill is instructed to write files to the local file system using a dynamically generated filename (SKILL.md, step 6).
- Sanitization: No sanitization or validation is applied to the input content or the derived filename, increasing the risk of path manipulation or content injection.
Audit Metadata