solo-domain
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates for shell commands using
curlandwhoisto verify if names are registered as domains or in app stores. - [EXTERNAL_DOWNLOADS]: Queries data from well-known and reputable services including
itunes.apple.com,github.com, andrdap.org. These network operations are necessary for the skill's stated purpose. - [REMOTE_CODE_EXECUTION]: Employs a pipe from
curltopython3to parse JSON metadata from the Apple App Store. The Python code is defined locally within the skill and serves as a parser for data returned by a trusted service. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill retrieves application names from the App Store and fetches the HTML
<title>tags of existing websites. - Boundary markers: No explicit instructions are provided to the agent to treat this external content as untrusted data.
- Capability inventory: The skill uses the
Bashtool to perform network queries and process data. - Sanitization: External application names are normalized using regular expressions in a local Python processing script.
Audit Metadata