download
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch content from user-provided URLs. This allows arbitrary files to be downloaded from the internet into the local environment. - [COMMAND_EXECUTION]: The skill utilizes the
exectool to execute shell commands, specificallycurl, to perform file downloads. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources, creating an attack surface for indirect prompt injection.
- Ingestion points: Data is fetched from arbitrary URLs provided as arguments to the
/downloadcommand (SKILL.md). - Boundary markers: Absent. The skill does not instruct the agent to use delimiters or to treat the downloaded content as non-executable data.
- Capability inventory: The skill uses the
exectool to runcurl(SKILL.md). - Sanitization: Absent. No validation or sanitization of the downloaded file's content is performed.
Audit Metadata