silence-cut
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
auto-editorandffprobeshell commands to process audio files. This is the primary and intended purpose of the skill. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided variables into shell commands.
- Ingestion points: User-supplied values for
<input>,<threshold>,<margin>, and<output>are used in the procedure inSKILL.md. - Boundary markers: None are used to separate untrusted input from the command structure.
- Capability inventory: The skill uses subprocess calls to execute CLI tools.
- Sanitization: There are no instructions provided to the agent to sanitize or validate these inputs before command construction.
Audit Metadata