cco-digest
Warn
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a Node.js script using the
Bashtool with the$ARGUMENTSvariable interpolated directly into the command line. - Ingestion Point: The
$ARGUMENTSvariable inSKILL.mdis populated by user-supplied input. - Capability: The skill uses the
Bashtool to run commands on the system. - Evidence:
node ${CLAUDE_PLUGIN_ROOT}/src/digest.js $ARGUMENTSinSKILL.md. - Risk: If the underlying platform does not sanitize the
$ARGUMENTSvalue, an attacker could provide input containing shell metacharacters (e.g.,;,|,&, or backticks) to execute unauthorized arbitrary commands.
Audit Metadata