web-to-markdown
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing shell commands to perform its core functionality, including
web2md,mkdir, andnpmfor installation and build processes. The skill instructions assume the existence of a local project at~/workspace/softaworks/projects/web2md. - [INDIRECT_PROMPT_INJECTION]: The skill fetches and converts content from arbitrary URLs provided by the user, creating a surface for indirect prompt injection attacks.
- Ingestion points: Data enters the agent context via the
web2mdtool which fetches and converts web pages from external URLs. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the converted content.
- Capability inventory: The skill can execute shell commands, perform file system operations, and install/link local packages.
- Sanitization: No explicit sanitization of the fetched content is mentioned beyond the standard conversion to Markdown performed by the underlying tool.
Audit Metadata