crawlberg-mapping-urls
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process data from external, untrusted websites, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The
crawlberg map <url>command retrievessitemap.xmlfiles and HTML content from remote servers specified by the user or discovered during mapping (SKILL.md). - Boundary markers: The instructions do not specify the use of boundary markers or protective delimiters when the agent processes the discovered URLs or site metadata.
- Capability inventory: The skill enables shell command execution (
crawlberg) and subsequent processing of the output, which may be piped to other tools likejqor written to files. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from remote sites before it is incorporated into the agent's context.
- [COMMAND_EXECUTION]: The skill utilizes the
crawlbergcommand-line interface for web mapping and enumeration. As this is the core functionality provided by the vendor (xberg-io), the command execution itself is expected behavior for the tool's intended use case.
Audit Metadata